© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3444
    Prev
    Next
    INDEX
    Explanations

    elements related to images and buttons in a code context

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

    image tags and their source attributes in HTML and code.

    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
    AndEndTag
    -0.91
    Geplaatst
    -0.70
    quiel
    -0.67
    ution
    -0.66
    InputBorder
    -0.66
    Lähteet
    -0.65
     Савезне
    -0.65
    TemporalType
    -0.65
     myſelf
    -0.64
    quelize
    -0.63
    POSITIVE LOGITS
    iconque
    0.33
    lrrr
    0.28
     Atty
    0.28
    ctx
    0.25
     tmp
    0.24
     Voyez
    0.24
    wartet
    0.24
    frm
    0.23
    stk
    0.23
    idx
    0.23
    Activations Density 0.506%

    No Known Activations