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. 15-GEMMASCOPE-RES-16K
    6. 8558
    Prev
    Next
    INDEX
    Explanations

    requests or polite prompts for information or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.67
    ation
    -0.63
    كويكب
    -0.62
    _()
    -0.62
     Nullable
    -0.62
    Writes
    -0.60
    bison
    -0.59
     <<<<<<<<<<<<<<
    -0.58
    ia
    -0.57
    vía
    -0.57
    POSITIVE LOGITS
     please
    1.09
     Please
    0.97
    Please
    0.95
    please
    0.92
     PLEASE
    0.91
    Pls
    0.87
     pls
    0.83
    PLEASE
    0.81
     Bitte
    0.79
     Pls
    0.77
    Activations Density 0.040%

    No Known Activations