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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6228
    Prev
    Next
    INDEX
    Explanations

    terms related to possession and the frequency of brief mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.81
    Jeografia
    -0.70
     Infórmanos
    -0.66
     Taktlose
    -0.66
    Билгалдахарш
    -0.63
    transQ
    -0.63
     ModelExpression
    -0.63
     الرياضيه
    -0.63
    şört
    -0.62
    $_['
    -0.60
    POSITIVE LOGITS
     possession
    1.12
    possession
    0.83
     Possession
    0.82
     possessed
    0.80
     possess
    0.79
     possesses
    0.77
     possessing
    0.77
    Poss
    0.76
     preview
    0.74
     brief
    0.71
    Activations Density 0.073%

    No Known Activations