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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13514
    Prev
    Next
    INDEX
    Explanations

    URLs, particularly focusing on the patterns and structure of web addresses

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

    References/citations, often bracketed and numerical

    np_acts-logits-general · gemini-2.0-flash

    introduce evidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.54
     autorytatywna
    -0.51
     continúas
    -0.49
    ГЛА
    -0.48
     CanadaChoose
    -0.48
    collana
    -0.45
     CURIAM
    -0.44
    oare
    -0.43
    pulsera
    -0.43
     <=",
    -0.43
    POSITIVE LOGITS
     препратки
    0.45
    ftance
    0.43
    🔕
    0.42
    ⟭
    0.41
     estekak
    0.40
    oneofs
    0.36
    CharacterOffset
    0.36
    oplayer
    0.35
     cad
    0.35
     ✭✭
    0.34
    Activations Density 0.885%

    No Known Activations