© 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. 11766
    Prev
    Next
    INDEX
    Explanations

    references to classifications and novel contributions in theoretical discussions

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

    the word "Another" at the beginning of sentences or paragraphs.

    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
    Datuak
    -0.57
    Cul
    -0.47
    HasAnnotation
    -0.45
    лтемелер
    -0.45
    лтамалар
    -0.45
     pinulongan
    -0.44
    Defin
    -0.42
    ⓘ
    -0.42
     combos
    -0.42
     calib
    -0.42
    POSITIVE LOGITS
     Schluß
    0.60
     interesantes
    0.60
     cieka
    0.57
     approach
    0.57
     intéressante
    0.56
     interesting
    0.55
     intriguing
    0.53
     interesante
    0.53
     circonst
    0.52
     phénomènes
    0.52
    Activations Density 1.562%

    No Known Activations