© 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. 18-GEMMASCOPE-RES-16K
    11. 894
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and technology, specifically focusing on concepts around rendering and spell casting

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

    Punctuation and two-character fragments

    np_acts-logits-general · gemini-2.0-flash

    rank and tier specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NUMX
    -1.17
    .",
    -0.97
    ."));
    -0.95
    .")
    -0.95
    ".
    -0.94
     فريبيس
    -0.92
     وتسجيلات
    -0.91
    .")]
    -0.91
    ."]
    -0.91
    $")
    -0.91
    POSITIVE LOGITS
    :
    1.71
     –
    1.39
     -
    1.32
     :
    1.29
    ：
    1.12
     —
    1.09
     =
    1.07
     ->
    0.96
     --
    0.91
    ):
    0.90
    Activations Density 1.180%

    No Known Activations