© 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. 2367
    Prev
    Next
    INDEX
    Explanations

    conjectures or statements regarding potential outcomes or claims

    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
    transQ
    -0.50
    LookAnd
    -0.50
    Said
    -0.47
    aarrggbb
    -0.44
    帖最后由
    -0.43
     Photocase
    -0.42
     noDo
    -0.41
    awtextra
    -0.41
    Попис
    -0.41
    TabStop
    -0.41
    POSITIVE LOGITS
     say
    1.07
     describe
    1.04
     point
    1.02
     cite
    0.91
     tell
    0.85
     explain
    0.85
     state
    0.84
     indicate
    0.81
     outline
    0.81
     suggest
    0.80
    Activations Density 1.152%

    No Known Activations