© 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. 468
    Prev
    Next
    INDEX
    Explanations

    technical terms and metrics related to data analysis and experimental results

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

    "of each" or "at each"

    np_acts-logits-general · gemini-2.0-flash

    corresponding or respective

    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
    IGR
    -0.41
    ako
    -0.40
    ждународ
    -0.39
    Even
    -0.38
    ged
    -0.37
    Ged
    -0.36
    х
    -0.35
    even
    -0.35
    forRoot
    -0.35
    apunov
    -0.35
    POSITIVE LOGITS
     respective
    1.96
     corresponding
    1.95
    corresponding
    1.76
    respective
    1.73
     correspondiente
    1.59
     jeweiligen
    1.58
     соответству
    1.50
    相应
    1.47
     Corresponding
    1.44
     entsprechenden
    1.43
    Activations Density 0.890%

    No Known Activations