© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5980
    Prev
    Next
    INDEX
    Explanations

    references to organizational structures and hierarchical relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX and "&" symbols

    np_acts-logits-general · gemini-2.0-flash

    math and special characters like `&`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.94
    .
    -0.79
    -
    -0.77
    :
    -0.69
    (
    -0.67
     to
    -0.63
     
    -0.61
    )
    -0.57
     –
    -0.57
    ]
    -0.57
    POSITIVE LOGITS
    amp
    1.68
    quot
    1.38
     Cæsar
    1.35
     myſelf
    1.30
     itſelf
    1.26
    ndash
    1.20
    mdash
    1.18
     himſelf
    1.17
    nbsp
    1.16
     purpoſe
    1.15
    Activations Density 0.080%

    No Known Activations