© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 6095
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to "pre" and their significance in various contexts

    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
    rmtree
    -0.63
     compter
    -0.55
    MethodManager
    -0.54
    ⓘ
    -0.53
    rrggbb
    -0.52
     doch
    -0.49
    tonode
    -0.49
    riwal
    -0.48
    KommentareTeilen
    -0.47
     unknownFields
    -0.47
    POSITIVE LOGITS
     pre
    0.78
    pre
    0.69
    Pre
    0.59
     PRE
    0.58
     pré
    0.58
    出版年
    0.56
     dawn
    0.56
    StoryboardSegue
    0.54
     Pre
    0.54
     مرئيه
    0.53
    Activations Density 0.116%

    No Known Activations