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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1428
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and syntax used for mathematical formatting in documents

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

    LaTeX code snippets

    np_acts-logits-general · gemini-2.0-flash

    mathematical and code syntax"}, \quad \text<0xE2><0x80><0x94> math and code syntax

    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
    })));
    -0.50
    HtmlAttribute
    -0.48
    "]}
    -0.47
    เทศ
    -0.44
    attuale
    -0.44
    ufficio
    -0.43
    )}>
    -0.42
    )』
    -0.42
     \%$\\
    -0.42
    万美元
    -0.42
    POSITIVE LOGITS
     HasFactory
    0.75
    dafx
    0.71
    Autoritní
    0.61
     OFDb
    0.61
    رشف
    0.60
    UrlResolution
    0.60
    XmlEnum
    0.59
    хьтан
    0.58
    sidemargin
    0.58
    ServletConfig
    0.57
    Activations Density 0.112%

    No Known Activations