© 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. 22-GEMMASCOPE-RES-16K
    6. 8937
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references, particularly focusing on sections and citations

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

    Within parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    spices, science or legal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelSerializer
    -0.51
    jsonwebtoken
    -0.46
    qrstuvwxyz
    -0.46
    tribune
    -0.43
     Washington
    -0.43
    HAEL
    -0.43
     setTotal
    -0.42
    ithin
    -0.42
    🦃
    -0.41
    NegativeButton
    -0.41
    POSITIVE LOGITS
    :✨
    1.26
    ########.
    0.81
    Datuak
    0.78
    XmlType
    0.70
    tvguidetime
    0.69
     caprice
    0.66
     INTERESAR
    0.65
    UnusedPrivate
    0.63
     otomatig
    0.62
    oredCriteria
    0.61
    Activations Density 0.068%

    No Known Activations