© 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. 24-GEMMASCOPE-RES-16K
    11. 1129
    Prev
    Next
    INDEX
    Explanations

    mentions of variable values in code

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

    "value" and variants

    np_acts-logits-general · gemini-2.0-flash

    value: or "value"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    st
    -0.51
    <h1>
    -0.51
    9
    -0.48
    <
    -0.47
    nd
    -0.46
     Humphreys
    -0.46
     Grims
    -0.45
     Schrö
    -0.45
    3
    -0.45
    not
    -0.45
    POSITIVE LOGITS
     Value
    1.19
     VALUE
    1.13
     value
    1.08
    Value
    1.07
    value
    1.01
     getValue
    0.98
    VALUE
    0.97
     Values
    0.96
    ValueStyle
    0.95
     valu
    0.91
    Activations Density 0.163%

    No Known Activations