© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9045
    Prev
    Next
    INDEX
    Explanations

    elements of code and structural components in programming

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

    "region" within hexadecimal code mappings

    np_acts-logits-general · gemini-2.0-flash

    region:

    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
    )");
    -1.06
     виправивши
    -1.05
    !")
    -0.95
    .",
    -0.92
    .")
    -0.91
    )";
    -0.88
    $")
    -0.86
    %");
    -0.84
     ]
    -0.83
    ."]
    -0.83
    POSITIVE LOGITS
    _
    0.72
     PLWABN
    0.48
    Fa
    0.46
    less
    0.43
     terk
    0.43
     도
    0.43
    Te
    0.42
     =
    0.42
    Mo
    0.42
    (
    0.41
    Activations Density 0.378%

    No Known Activations