© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12822
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structure within the document

    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
    المناصب
    -0.77
     Италијани
    -0.76
    richTextPanel
    -0.72
    SharedCtor
    -0.71
     EconPapers
    -0.65
    bitField
    -0.63
    AlterField
    -0.62
    transQ
    -0.59
     StringTokenizer
    -0.58
    Rhestr
    -0.58
    POSITIVE LOGITS
    didReceive
    0.57
     }}"></
    0.56
    ("</
    0.56
    </table>
    0.55
    <eos>
    0.54
    ApplicationTests
    0.53
    Respectfully
    0.52
    </tbody>
    0.52
     "]";
    0.50
     filepath
    0.50
    Activations Density 0.074%

    No Known Activations