© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 250
    Prev
    Next
    INDEX
    Explanations

    meanings and definitions of names, especially those related to natural elements and mythological concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases where a term is followed by "meaning" to indicate a translation or definition of a word or concept.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The word "meaning" and related explanations of what words or phrases signify.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propuesto
    -0.37
     ocupado
    -0.36
     actuaciones
    -0.34
     expuesto
    -0.33
     dessutom
    -0.33
    accesso
    -0.33
     oír
    -0.32
     dispuesto
    -0.32
     erfahren
    -0.31
     erwarten
    -0.31
    POSITIVE LOGITS
     OMITBAD
    0.76
     ModelExpression
    0.74
     validamos
    0.73
    ImageContext
    0.73
     Italijanski
    0.72
     ujednoznacz
    0.71
    ResponseWriter
    0.68
    EndGlobal
    0.67
    FieldDescriptor
    0.67
    Autoritní
    0.67
    Activations Density 0.279%

    No Known Activations