© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14206
    Prev
    Next
    INDEX
    Explanations

    references to challenges, difficulties, and imperfections in various contexts

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

    Punctuation, especially commas and periods

    np_acts-logits-general · gemini-2.0-flash

    inconsistency and differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     togg
    -0.40
    feier
    -0.39
    }));
    -0.38
    togg
    -0.37
     виправивши
    -0.37
    ',$
    -0.36
     Aqu
    -0.35
     stra
    -0.35
    *}{
    -0.35
     tou
    -0.35
    POSITIVE LOGITS
    styleType
    0.63
    Autoritní
    0.53
    IntoConstraints
    0.52
    没关系
    0.51
     paraître
    0.50
    retudo
    0.50
    richTextPanel
    0.46
    Bibliograf
    0.46
    fficients
    0.45
     ſche
    0.45
    Activations Density 0.695%

    No Known Activations