© 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. 5706
    Prev
    Next
    INDEX
    Explanations

    programming functions and methods related to data manipulation and output

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

    Code snippets with "append" or "println"

    np_acts-logits-general · gemini-2.0-flash

    programming append print calls

    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
    AsUp
    -0.69
    (".",
    -0.63
    ('.',
    -0.61
     otomatig
    -0.58
    ("/",
    -0.53
     publicitaires
    -0.51
    ("",
    -0.50
    balleur
    -0.48
    port
    -0.47
    VertexAttrib
    -0.47
    POSITIVE LOGITS
     AssemblyTitle
    0.77
    Hauptartikel
    0.76
    AccessorTable
    0.68
    ."]
    0.65
    NUMX
    0.62
    NameInMap
    0.62
    Архівовано
    0.61
    OrWhiteSpace
    0.61
    bibfield
    0.60
    $")
    0.60
    Activations Density 0.078%

    No Known Activations