© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 64815
    Prev
    Next
    INDEX
    Explanations

    concepts related to dog behavior and training

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

    dog instincts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Económica
    -0.38
    ::__
    -0.38
     concor
    -0.36
     Exclusive
    -0.36
    Qualifier
    -0.35
    Argb
    -0.35
     stras
    -0.34
    reactstrap
    -0.34
    Exclusive
    -0.34
     Popular
    -0.34
    POSITIVE LOGITS
     instinct
    0.77
     instincts
    0.68
     instinctive
    0.66
     Chwiliwch
    0.64
    本能
    0.62
     instinctively
    0.62
     صوتيه
    0.60
     Instinct
    0.58
     natürlichen
    0.55
     naturally
    0.54
    Activations Density 0.049%

    No Known Activations