© 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. 3989
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and evidence in contexts involving legality or regulatory frameworks

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

    Text followed by "Q:" or "MEMORANDUM"

    np_acts-logits-general · gemini-2.0-flash

    MEMORANDUM J

    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
    <sup>
    -0.55
     I
    -0.50
     and
    -0.48
     
    -0.47
     (
    -0.46
     Bon
    -0.46
     letter
    -0.45
    tamin
    -0.45
    ดัง
    -0.45
     bid
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.92
     EconPapers
    0.90
     typelib
    0.88
    ंदीखरीदारी
    0.82
    Datuak
    0.76
    testens
    0.74
     [*]
    0.74
    ftagPool
    0.73
    TagHelper
    0.72
    الإنجليزية
    0.71
    Activations Density 0.414%

    No Known Activations