© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7097
    Prev
    Next
    INDEX
    Explanations

    sentences that emphasize personal reflections or opinions

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

    "I" followed by a verb of opinion/thought

    np_acts-logits-general · gemini-2.0-flash

    expressing belief or doubt

    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
     CreateTagHelper
    -0.79
    IntoConstraints
    -0.69
    nanoTime
    -0.57
    aarrggbb
    -0.55
    lalu
    -0.55
    millimeters
    -0.53
    Commit
    -0.53
    atoto
    -0.53
     Reſ
    -0.52
     AssemblyTitle
    -0.51
    POSITIVE LOGITS
     guess
    1.66
     guessing
    1.45
     suspect
    1.43
     doubt
    1.39
     presume
    1.38
    guess
    1.33
     assume
    1.30
     imagine
    1.21
     Guess
    1.19
     guesses
    1.18
    Activations Density 0.370%

    No Known Activations