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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7318
    Prev
    Next
    INDEX
    Explanations

    code structures and flow control within programming contexts

    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
     Efq
    -1.12
     myſelf
    -1.02
     Jefus
    -0.99
     poffe
    -0.99
     Majefty
    -0.97
     resourceCulture
    -0.96
     Monfieur
    -0.95
    featureID
    -0.94
    WriteTagHelper
    -0.94
     ſeveral
    -0.93
    POSITIVE LOGITS
    ../../
    0.56
     ・
    0.56
    └
    0.55
    displayquote
    0.55
     Ko
    0.55
    sprogramm
    0.53
     At
    0.53
    vaient
    0.52
    itemize
    0.51
    일에
    0.51
    Activations Density 0.089%

    No Known Activations