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 - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 13304
    Prev
    Next
    INDEX
    Explanations

    historical references to development and land use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -1.33
     myſelf
    -1.11
     purpoſe
    -1.05
     Theſe
    -1.03
    ThroughAttribute
    -1.00
     ſche
    -1.00
     Monfieur
    -0.97
     Majefty
    -0.96
     ―――――
    -0.96
     Efq
    -0.94
    POSITIVE LOGITS
     til
    0.45
     ta
    0.44
     si
    0.42
    foro
    0.42
     var
    0.41
     -
    0.41
     building
    0.40
    lev
    0.39
    機能
    0.39
     Col
    0.39
    Activations Density 0.365%

    No Known Activations