© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 1229
    Prev
    Next
    INDEX
    Explanations

    discussions related to legal frameworks and procedural matters

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

    comparative statements using "as" to draw parallels or establish equivalence between ideas.

    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
     ModelExpression
    -0.54
     OMITBAD
    -0.45
    pholes
    -0.44
    webElementXpaths
    -0.42
    Према
    -0.42
    Datuak
    -0.40
    CrossRef
    -0.39
    RTCK
    -0.38
    stylers
    -0.38
    PathVariable
    -0.38
    POSITIVE LOGITS
     here
    4.03
     aquí
    3.03
    here
    2.92
     здесь
    2.86
     Here
    2.72
    Here
    2.69
     aqui
    2.63
     ici
    2.59
     هنا
    2.58
     aici
    2.55
    Activations Density 1.986%

    No Known Activations