© 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. 1744
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to biological processes and experimental methodologies

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

    imitation or resemblance

    np_acts-logits-general · gemini-2.0-flash

    mimic, imitate, resemble

    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
    expandindo
    -0.61
     légende
    -0.58
    gerea
    -0.53
     '\\;'
    -0.47
    encji
    -0.46
    нительно
    -0.46
    éndolo
    -0.46
    ToBounds
    -0.46
     rentrée
    -0.45
     vectorielle
    -0.45
    POSITIVE LOGITS
     mimic
    2.16
     mimicking
    2.03
     mimics
    1.97
     imitate
    1.95
     imitating
    1.92
     imitation
    1.83
     imit
    1.83
     emulate
    1.78
     imitated
    1.75
     resemblance
    1.67
    Activations Density 0.709%

    No Known Activations