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. 3-GEMMASCOPE-RES-16K
    6. 12287
    Prev
    Next
    INDEX
    Explanations

    requests for action or feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    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
    -0.76
     onData
    -0.74
     ζω
    -0.68
     virke
    -0.67
    كويكب
    -0.67
     quella
    -0.65
     Herd
    -0.63
    vB
    -0.61
    GMENT
    -0.61
    ation
    -0.60
    POSITIVE LOGITS
     please
    2.92
     Please
    2.60
    please
    2.54
    Please
    2.48
     PLEASE
    2.41
    PLEASE
    2.15
     pls
    2.09
     plz
    1.81
     Pls
    1.81
     Bitte
    1.76
    Activations Density 0.040%

    No Known Activations