© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 6363
    Prev
    Next
    INDEX
    Explanations

    references to API and UI components in a technical or programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.64
    TB
    -0.57
    SB
    -0.56
    SV
    -0.54
    TV
    -0.53
    ND
    -0.52
    SM
    -0.52
    MP
    -0.51
    TT
    -0.51
    TZ
    -0.51
    POSITIVE LOGITS
    e
    0.36
    IsPostBack
    0.36
    tvguidetime
    0.35
    И
    0.34
    IN
    0.33
    setVerticalGroup
    0.33
    ました
    0.32
    nex
    0.32
    iI
    0.31
    ه
    0.31
    Activations Density 0.345%

    No Known Activations