Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1058
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional struggle and hardship

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

    Follows words like "the", "a", or prepositions

    np_acts-logits-general · gemini-2.0-flash

    slave traders, to help

    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
     IRS
    -0.43
     columb
    -0.38
     considérons
    -0.37
    drawSprites
    -0.37
    鏈
    -0.37
    inite
    -0.36
     soviet
    -0.36
     GED
    -0.36
    ospels
    -0.36
    initely
    -0.35
    POSITIVE LOGITS
     ivelany
    0.77
     resourceCulture
    0.68
    ThroughAttribute
    0.61
     pinulongan
    0.60
     الحره
    0.56
    InitVars
    0.55
    évaluateur
    0.54
     HasFactory
    0.52
     initComponents
    0.51
    RegressionTest
    0.51
    Activations Density 0.064%

    No Known Activations