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. 19-GEMMASCOPE-RES-16K
    6. 4280
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about technical subjects and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ResumeLayout
    -0.58
    labelledby
    -0.55
    öhne
    -0.50
    lloworld
    -0.49
    ImageIO
    -0.49
    lamabad
    -0.48
    runApp
    -0.47
    ]='\
    -0.46
    exels
    -0.44
    IDAE
    -0.44
    POSITIVE LOGITS
     what
    2.21
     how
    2.18
     What
    1.98
    what
    1.93
    What
    1.92
     How
    1.91
    How
    1.84
     why
    1.79
    how
    1.74
     WHAT
    1.60
    Activations Density 1.350%

    No Known Activations