© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1460
    Prev
    Next
    INDEX
    Explanations

    programming commands and functions related to managing tasks and networks

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

    Code snippets or code-related text

    np_acts-logits-general · gemini-2.0-flash

    I can

    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
     Administrativna
    -0.64
     AssemblyTitle
    -0.62
     Photocase
    -0.57
    GraphicsUnit
    -0.57
     Chwiliwch
    -0.52
    TypedDataSet
    -0.52
    IsContent
    -0.52
     wireType
    -0.50
    EDEFAULT
    -0.49
    VolleyError
    -0.48
    POSITIVE LOGITS
    liputi
    0.41
    出版年
    0.40
     Fakten
    0.39
     toekomst
    0.37
     plegable
    0.37
    aqui
    0.36
     phiên
    0.36
    here
    0.35
    horabuena
    0.35
     syntax
    0.35
    Activations Density 0.191%

    No Known Activations