Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14032
    Prev
    Next
    INDEX
    Explanations

    questions and phrases that prompt exploration and analysis of choices or conditions

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

    Question words

    np_acts-logits-general · gemini-2.0-flash

    questions and explanations

    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
    RectangleBorder
    -0.61
    UpInside
    -0.55
    esModule
    -0.55
    +#+#
    -0.51
    GEBURTSDATUM
    -0.51
    ⓧ
    -0.50
    .*")]
    -0.46
    setopt
    -0.46
    IBarButtonItem
    -0.46
     Adonis
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.62
     незавершена
    0.55
     мәкал
    0.39
    ględ
    0.39
     yourself
    0.39
    ?)
    0.38
    новниш
    0.38
    viembre
    0.37
     pel
    0.36
     contrasting
    0.36
    Activations Density 0.445%

    No Known Activations