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. 10382
    Prev
    Next
    INDEX
    Explanations

    references to success and failure 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
    rcParams
    -0.53
     OMITTED
    -0.50
    thrower
    -0.49
    ization
    -0.49
     rze
    -0.48
    <>("
    -0.46
    diğinde
    -0.45
    xhtml
    -0.45
    inputData
    -0.43
    ignants
    -0.43
    POSITIVE LOGITS
     stories
    0.87
     成功
    0.86
     rate
    0.79
    mybatisplus
    0.77
     Stories
    0.76
    OrFail
    0.75
     SUCCESS
    0.75
     Success
    0.74
    Stories
    0.73
     Failures
    0.73
    Activations Density 0.118%

    No Known Activations