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. 14027
    Prev
    Next
    INDEX
    Explanations

    sections related to policy and technical descriptions

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

    Preceding a number/policy/project/description

    np_acts-logits-general · gemini-2.0-flash

    section titles or document introductions

    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
     kasarigan
    -0.94
    DockStyle
    -0.80
    المناصب
    -0.74
     صوتيه
    -0.71
    Diwedd
    -0.71
     ब्रेकडाउन
    -0.71
    ContentAlignment
    -0.71
    GEBURTSDATUM
    -0.71
    MLLoader
    -0.69
    SharedDtor
    -0.66
    POSITIVE LOGITS
    IContainer
    0.34
    ục
    0.33
    ...
    0.32
     Mission
    0.31
    的一
    0.31
     מט
    0.30
    кура
    0.30
     identification
    0.29
    的目的
    0.29
    Mission
    0.28
    Activations Density 0.177%

    No Known Activations