Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10491
    Prev
    Next
    INDEX
    Explanations

    recommendations for optimizing content creation strategies in relation to trending industry events

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

    "Peak" or a similar word

    np_acts-logits-general · gemini-2.0-flash

    peak or season

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnknownFieldSet
    -0.68
    tableFuture
    -0.65
     ostavi
    -0.63
    fjspx
    -0.57
    AlterField
    -0.56
    SharedCtor
    -0.55
    qrstuvwxyz
    -0.54
     ویکی‌پدی
    -0.52
     CreateTagHelper
    -0.52
     كومونز
    -0.52
    POSITIVE LOGITS
     peak
    1.87
    peak
    1.62
    Peak
    1.51
     peaks
    1.43
     Peak
    1.43
     PEAK
    1.27
     season
    1.26
     periods
    1.20
     period
    1.17
    peaks
    1.16
    Activations Density 0.191%

    No Known Activations