© 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-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 4794
    Prev
    Next
    INDEX
    Explanations

    academic terms and results related to mathematical theorems or proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.63
    InitVars
    -0.59
    ativement
    -0.57
     ModelExpression
    -0.57
    }">
    -0.57
    saraba
    -0.56
    }`)
    -0.55
    }`,
    -0.54
    instancetype
    -0.54
     calendriers
    -0.53
    POSITIVE LOGITS
    Datuak
    0.67
     gloire
    0.57
    UpInside
    0.56
     Dies
    0.55
     vermo
    0.52
     تضيفلها
    0.52
    kies
    0.50
     Versuch
    0.50
    viewDidLoad
    0.49
     EventArgs
    0.49
    Activations Density 2.603%

    No Known Activations