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. 16164
    Prev
    Next
    INDEX
    Explanations

    references to anecdotes or personal stories

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

    Follows personal anecdotes or stories

    np_acts-logits-general · gemini-2.0-flash

    telling a story once

    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
    primarily
    -0.55
     Hopefully
    -0.54
     primarily
    -0.53
    Hopefully
    -0.53
    saraba
    -0.50
    ありがとうございます
    -0.50
     Further
    -0.49
     continuing
    -0.47
    Further
    -0.47
     dals
    -0.46
    POSITIVE LOGITS
     once
    2.51
    once
    2.15
    Once
    1.93
     Once
    1.87
     ONCE
    1.84
    ONCE
    1.74
     pernah
    1.67
     kiedyś
    1.52
     ooit
    1.39
     einmal
    1.38
    Activations Density 0.422%

    No Known Activations