© 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. 21-GEMMASCOPE-RES-16K
    11. 12348
    Prev
    Next
    INDEX
    Explanations

    references to blocks, possibly in a programming or organizational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.69
    <caption>
    -0.68
    WebVitals
    -0.66
     وتسجيلات
    -0.66
    DrawerToggle
    -0.65
    ็จ
    -0.64
     للاسماء
    -0.63
    ंदीखरीदारी
    -0.63
    %)$
    -0.62
     Ory
    -0.61
    POSITIVE LOGITS
     blocks
    1.35
     Blocks
    1.21
    blocks
    1.21
     BLOCK
    1.20
    Blocks
    1.15
     block
    1.15
     Block
    1.10
    BLOCK
    1.09
    block
    1.07
     bloc
    0.98
    Activations Density 0.081%

    No Known Activations