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. 11750
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the significance or exceptional nature of something

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

    Adverbs followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    especially or particularly certain contexts

    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
     createSlice
    -0.71
     ModelExpression
    -0.62
    +#+#
    -0.60
     EconPapers
    -0.59
    aarrggbb
    -0.57
     propOrder
    -0.57
     asemenea
    -0.55
    httphttps
    -0.52
    ukone
    -0.51
    ……"
    -0.50
    POSITIVE LOGITS
     during
    1.27
     from
    1.18
     in
    1.13
     for
    1.11
     when
    1.10
     with
    1.04
    during
    1.03
     via
    1.00
     at
    0.99
     towards
    0.95
    Activations Density 0.799%

    No Known Activations