© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10810
    Prev
    Next
    INDEX
    Explanations

    terms related to maritime and operational contexts, as well as artistic expressions involving embroidery

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

    Word before "vessel," "Pixel," or similar capitalized words

    np_acts-logits-general · gemini-2.0-flash

    seismic vessel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prez
    -0.30
    ่วน
    -0.28
     bậc
    -0.28
     Förder
    -0.28
     overall
    -0.28
    overall
    -0.28
     Tym
    -0.27
    пуска
    -0.27
    sbin
    -0.27
    rish
    -0.27
    POSITIVE LOGITS
    AnchorStyles
    0.63
    principalColumn
    0.62
    الحياه
    0.62
    dafx
    0.56
    évaluateur
    0.56
     auffi
    0.54
     queſta
    0.54
    CloseOperation
    0.54
     jScrollPane
    0.54
     myſelf
    0.54
    Activations Density 0.276%

    No Known Activations