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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5536
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data manipulation terms

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

    Variables named "x" or "v"

    np_acts-logits-general · gemini-2.0-flash

    lambda expressions and code constructs

    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
    '][$
    -0.78
    ']],
    -0.76
    "])
    -0.73
    `{.
    -0.71
    )++;
    -0.71
    "],
    -0.70
    '];?>
    -0.69
    "]);
    -0.69
     }}}
    -0.68
    '}),
    -0.68
    POSITIVE LOGITS
     فريبيس
    0.60
     članak
    0.60
     noDo
    0.58
    NonNull
    0.57
    erializer
    0.56
     =>
    0.53
     iprot
    0.53
     لينك
    0.53
     grecque
    0.53
     quæ
    0.51
    Activations Density 0.201%

    No Known Activations