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. 6779
    Prev
    Next
    INDEX
    Explanations

    references to the structure of code or file paths in a programming or software context

    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
     jScrollPane
    -0.75
    .'.
    -0.69
    }.
    -0.66
    ),'
    -0.65
    ).'
    -0.65
    _.
    -0.63
    .".
    -0.62
    ').
    -0.61
    *.
    -0.61
    /*.
    -0.61
    POSITIVE LOGITS
    \
    0.90
    extAlignment
    0.81
    AutoresizingMask
    0.75
     BoxDecoration
    0.69
    PrototypeOf
    0.67
    — 
    0.66
    ioutil
    0.65
     itſelf
    0.63
     Etrus
    0.61
     "..\..\
    0.61
    Activations Density 0.026%

    No Known Activations