© 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. 11202
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to algorithms and probabilistic models

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

    before actions, assignments, or iterations

    np_acts-logits-general · gemini-2.0-flash

    defining or assigning elements

    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
    ....)
    -0.47
    "....
    -0.46
    DebuggerStep
    -0.46
    [/
    -0.46
    DebuggerNonUser
    -0.45
    riz
    -0.44
    !!”
    -0.42
     zucca
    -0.42
    .[/
    -0.42
    amet
    -0.42
    POSITIVE LOGITS
     corresponding
    0.71
    pushFollow
    0.70
     Algorithm
    0.69
     update
    0.69
     esternos
    0.69
    женские
    0.67
    DotNetBar
    0.67
     conflits
    0.67
    SerializedSize
    0.67
     belonging
    0.66
    Activations Density 2.133%

    No Known Activations