© 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. 10002
    Prev
    Next
    INDEX
    Explanations

    references to significant features or attributes associated with entities or objects

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

    the word "the" preceding descriptive nouns or adjectives that convey positive qualities or desirable attributes.

    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
     skoro
    -0.40
     Exactos
    -0.40
     másik
    -0.38
     роки
    -0.35
     saites
    -0.34
    tadiene
    -0.33
     مؤرشف
    -0.32
    ところで
    -0.32
     بهذا
    -0.31
     呢
    -0.31
    POSITIVE LOGITS
     widest
    0.79
     same
    0.77
     finest
    0.72
     broadest
    0.71
     equivalent
    0.69
     smallest
    0.69
     gleichen
    0.68
     cleanest
    0.68
     highest
    0.67
     usual
    0.67
    Activations Density 0.961%

    No Known Activations