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. 31-GEMMASCOPE-RES-16K
    6. 9219
    Prev
    Next
    INDEX
    Explanations

    timestamps and date-related metadata

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

    dates in the format YYYY-MM-DD.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -1.02
    RenderAtEndOf
    -0.77
    haikusbot
    -0.67
    Географиясе
    -0.66
    MockBean
    -0.65
    Aholisi
    -0.65
    يميديا
    -0.64
    modb
    -0.63
    verwijspagina
    -0.62
    InjectAttribute
    -0.59
    POSITIVE LOGITS
    DATE
    0.45
     DATE
    0.44
     Oct
    0.44
    Date
    0.44
     Date
    0.44
     Apr
    0.43
     Nov
    0.41
     date
    0.40
    date
    0.40
     Fri
    0.39
    Activations Density 0.234%

    No Known Activations