© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6536
    Prev
    Next
    INDEX
    Explanations

    terms related to peaks and fluctuations in data

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

    "peak" or related terms

    np_acts-logits-general · gemini-2.0-flash

    peak of, peak at, peak with

    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
     Reverso
    -0.59
     betweenstory
    -0.50
    étaire
    -0.48
     fince
    -0.48
     caster
    -0.48
     tatu
    -0.46
    aarrggbb
    -0.46
    olingo
    -0.46
     Mose
    -0.45
     casters
    -0.45
    POSITIVE LOGITS
     peak
    2.63
    peak
    2.23
    Peak
    2.10
     peaks
    2.10
     Peak
    2.08
     peaking
    2.00
     peaked
    1.98
     PEAK
    1.83
    ピーク
    1.70
    peaks
    1.61
    Activations Density 0.392%

    No Known Activations