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. 23-GEMMASCOPE-RES-16K
    6. 6234
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.99
    出版年
    -0.88
    findpost
    -0.86
     تضيفلها
    -0.82
    帖最后由
    -0.81
     useAppContext
    -0.81
    >{@
    -0.80
     onCreateView
    -0.80
     ExecuteAsync
    -0.78
    tagHelperRunner
    -0.75
    POSITIVE LOGITS
    <eos>
    0.47
    ↵↵
    0.46
     botanique
    0.45
     elef
    0.45
     energético
    0.41
     azar
    0.40
     Gleich
    0.40
    ↵↵↵
    0.40
     ochi
    0.40
     chrétienne
    0.40
    Activations Density 0.080%

    No Known Activations