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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4104
    Prev
    Next
    INDEX
    Explanations

    references to 'block' in various contexts, indicating a focus on blocking actions or items

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

    "block" or its variations

    np_acts-logits-general · gemini-2.0-flash

    block party, block heater, block arrows

    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
    mazoo
    -0.67
    %)$
    -0.66
    ็จ
    -0.64
     Ory
    -0.63
    <caption>
    -0.63
     Miel
    -0.63
     وتسجيلات
    -0.62
    HttpFoundation
    -0.61
    DrawerToggle
    -0.61
     للاسماء
    -0.60
    POSITIVE LOGITS
     blocks
    1.39
     BLOCK
    1.28
     Blocks
    1.26
    blocks
    1.25
    Blocks
    1.22
     block
    1.20
     Block
    1.19
    BLOCK
    1.16
    block
    1.10
    Block
    1.05
    Activations Density 0.090%

    No Known Activations