© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 704
    Prev
    Next
    INDEX
    Explanations

    sentences that contain a specific focus on initial conditions or statuses of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anglès
    -0.67
     /\.(
    -0.65
    ghold
    -0.65
     Савезне
    -0.64
     Madden
    -0.63
    mopol
    -0.63
    tempuran
    -0.60
    scut
    -0.57
     Ry
    -0.56
     JG
    -0.56
    POSITIVE LOGITS
    ValueStyle
    0.81
     Púb
    0.75
    SequentialGroup
    0.70
     nemlig
    0.69
     BoxFit
    0.67
     Connectez
    0.67
     judiciales
    0.65
     dieß
    0.65
    >';
    
    0.65
     quæ
    0.65
    Activations Density 0.018%

    No Known Activations