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. 12495
    Prev
    Next
    INDEX
    Explanations

    references to code hosting platforms, particularly GitHub

    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
    AxisAlignment
    -1.21
    ValueStyle
    -1.11
    styleType
    -0.90
     <<<<<<<<<<<<<<
    -0.85
    +#+#
    -0.83
    AutoScaleMode
    -0.81
    astify
    -0.77
    GTCX
    -0.76
    RTHOOK
    -0.76
     MainAxisSize
    -0.74
    POSITIVE LOGITS
    git
    2.34
     git
    2.00
    Git
    1.87
     Git
    1.83
    GIT
    1.34
    github
    1.20
     github
    1.01
    GitHub
    1.00
     GIT
    0.97
     GitHub
    0.94
    Activations Density 0.019%

    No Known Activations