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. 13793
    Prev
    Next
    INDEX
    Explanations

    instances of proper nouns and specific names

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

    before "vol" or "fo" (likely fragments)

    np_acts-logits-general · gemini-2.0-flash

    words starting with 'fri', 'Gri', 'Bri', 'Cli', 'gli'

    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
    tagext
    -0.73
    triangleq
    -0.62
    JsonProperty
    -0.62
    ncy
    -0.60
    υσ
    -0.57
    ADVERTISEMENT
    -0.56
    хьтан
    -0.56
    Placa
    -0.55
    cated
    -0.54
    dataflow
    -0.54
    POSITIVE LOGITS
    i
    0.87
     onAnimation
    0.57
    iiiii
    0.55
    sizeCache
    0.51
    iM
    0.49
    optarg
    0.48
    ever
    0.47
    iiiiiiii
    0.47
     الاطلاع
    0.46
     asesinado
    0.46
    Activations Density 0.190%

    No Known Activations