Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56941
    Prev
    Next
    INDEX
    Explanations

    references to the Bootstrap framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zvuky
    -0.93
     tartalomajánló
    -0.90
    LEncoder
    -0.78
    WriteTagHelper
    -0.77
    interopRequire
    -0.74
    Jeografia
    -0.73
    '}),
    -0.73
    expandindo
    -0.73
    خصة
    -0.72
    帖最后由
    -0.72
    POSITIVE LOGITS
    bootstrap
    1.95
     bootstrap
    1.19
    Bootstrap
    1.05
     Bootstrap
    0.98
     bootstra
    0.73
    stdc
    0.65
    TM
    0.50
    BOOT
    0.49
     boots
    0.48
    Batman
    0.47
    Activations Density 0.003%

    No Known Activations