© 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. 0-GEMMASCOPE-RES-16K
    6. 7206
    Prev
    Next
    INDEX
    Explanations

    the name "Bob."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.98
    
    -0.86
     виправивши
    -0.85
     fathoms
    -0.81
    OGND
    -0.78
    ègre
    -0.76
     fairest
    -0.75
     greateſt
    -0.74
     Lasso
    -0.74
    parsedMessage
    -0.74
    POSITIVE LOGITS
     Bishop
    0.71
     Bob
    0.69
     async
    0.68
    Bob
    0.59
     It
    0.59
    bishop
    0.58
    async
    0.57
    tic
    0.54
    Bishop
    0.54
     ​​
    0.51
    Activations Density 0.101%

    No Known Activations