© 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. 14217
    Prev
    Next
    INDEX
    Explanations

    patterns or sequences of numerical data and references within the text

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

    First initial

    np_acts-logits-general · gemini-2.0-flash

    initials and abbreviations

    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
    BindingResult
    -0.85
    $")
    -0.81
    CodedInputStream
    -0.80
     >=",
    -0.79
    yntaxException
    -0.78
    }}/>
    -0.77
    𓃵
    -0.76
     AssemblyTitle
    -0.75
    TagMode
    -0.75
    /$',
    -0.75
    POSITIVE LOGITS
    E
    1.35
    A
    1.34
    R
    1.31
    C
    1.31
    B
    1.29
    L
    1.28
    M
    1.28
    J
    1.27
    S
    1.27
    P
    1.25
    Activations Density 0.510%

    No Known Activations