© 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. 24-GEMMASCOPE-RES-16K
    11. 486
    Prev
    Next
    INDEX
    Explanations

    statistical or mathematical references related to data analysis and econometrics

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

    Text before a journal reference volume number

    np_acts-logits-general · gemini-2.0-flash

    academic paper citations

    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
     protoimpl
    -0.88
     témoig
    -0.75
     myſelf
    -0.72
    <unused52>
    -0.70
    <unused28>
    -0.70
    <unused68>
    -0.70
    <unused74>
    -0.70
    <unused47>
    -0.70
    [@BOS@]
    -0.69
    <unused8>
    -0.69
    POSITIVE LOGITS
    zyst
    0.25
    bindingNavigator
    0.22
    paddingBottom
    0.21
    arResult
    0.21
    ว
    0.20
    jścia
    0.20
    exports
    0.20
     Öffentlichkeit
    0.20
     menos
    0.20
    ["
    0.20
    Activations Density 0.221%

    No Known Activations