© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9323
    Prev
    Next
    INDEX
    Explanations

    YAML formatted data structures and their components

    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
     $_"
    -0.90
    __':
    -0.85
     }}$}
    -0.82
    esterday
    -0.82
    __":
    -0.81
    ⿷
    -0.79
    )");
    -0.79
     Forumite
    -0.78
     سكانية
    -0.77
    )».
    -0.77
    POSITIVE LOGITS
    title
    0.74
    doc
    0.69
    url
    0.69
    id
    0.67
    text
    0.67
    size
    0.67
    file
    0.65
    type
    0.64
    content
    0.62
    <eos>
    0.61
    Activations Density 1.414%

    No Known Activations