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. 20-GEMMASCOPE-RES-16K
    6. 3531
    Prev
    Next
    INDEX
    Explanations

    references to specific projects or initiatives related to financial investment

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

    "the" followed by a season or time period

    np_acts-logits-general · gemini-2.0-flash

    points in time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SerializedName
    -0.51
    memoized
    -0.47
    BeginContext
    -0.44
    UVWXYZ
    -0.44
    клопе
    -0.41
    erv
    -0.40
    ::::::::
    -0.39
    adt
    -0.39
    ぶり
    -0.39
    jws
    -0.39
    POSITIVE LOGITS
     end
    0.85
     fall
    0.84
     Fall
    0.76
     dawn
    0.74
     onset
    0.68
     height
    0.66
     outbreak
    0.66
     beginning
    0.64
     recommandons
    0.64
     eve
    0.62
    Activations Density 0.257%

    No Known Activations