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. 17-GEMMASCOPE-RES-16K
    6. 11401
    Prev
    Next
    INDEX
    Explanations

    expressions of concern or potential issues regarding technology or software usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ☆☆☆☆
    -0.61
     كومونز
    -0.58
    GEST
    -0.57
    VIRONMENT
    -0.57
    CONSIN
    -0.57
    UFACT
    -0.56
    帖最后由
    -0.55
     Horv
    -0.55
    kug
    -0.54
    setupUi
    -0.54
    POSITIVE LOGITS
    ↵
    1.89
     […]
    1.59
    ↵↵
    1.33
    ,...
    1.26
     =
    
    1.23
     [...]
    1.20
    ',...
    1.15
    ...
    1.14
    [...]
    1.08
     ..."
    1.08
    Activations Density 8.935%

    No Known Activations