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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6198
    Prev
    Next
    INDEX
    Explanations

    SQL-related clauses and keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    AccessorTable
    -0.79
    -------------</
    -0.76
     Administrativna
    -0.72
    ViewFeatures
    -0.72
    InitVars
    -0.71
    enumii
    -0.71
    codecs
    -0.70
     незавершена
    -0.67
     мәкал
    -0.65
     <>",
    -0.65
    POSITIVE LOGITS
     linkovi
    0.57
     noqa
    0.55
    usercontent
    0.52
    timmung
    0.52
    ɹ
    0.50
     ostavi
    0.48
     گذ
    0.47
     sit
    0.47
     First
    0.46
    doria
    0.46
    Activations Density 0.144%

    No Known Activations