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. 10-GEMMASCOPE-RES-16K
    6. 2180
    Prev
    Next
    INDEX
    Explanations

    terms related to the first-come, first-serve principle and prioritized item ranking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.92
     '\\;'
    -0.81
    lapsingToolbar
    -0.78
    InputTagHelper
    -0.74
     nahilalakip
    -0.70
    MigrationBuilder
    -0.61
    ropol
    -0.59
     ELEV
    -0.59
    TypedDataSet
    -0.58
    AnchorStyles
    -0.58
    POSITIVE LOGITS
    Wikimedia
    0.48
     criterio
    0.47
     rather
    0.47
     method
    0.45
     surla
    0.45
    ьи
    0.45
     instead
    0.44
     अनुसार
    0.43
    ที่สุด
    0.42
    >//
    0.42
    Activations Density 0.591%

    No Known Activations