© 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. 17-GEMMASCOPE-RES-16K
    6. 8880
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to biological conditions and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.61
     propOrder
    -0.54
    ंदीखरीदारी
    -0.53
     }}"></
    -0.50
    PreAuthorize
    -0.48
    "]:
    -0.47
    KURZBESCHREIBUNG
    -0.46
    ertes
    -0.46
    webElement
    -0.45
    TagHelper
    -0.44
    POSITIVE LOGITS
     called
    2.72
    called
    2.34
     Called
    2.30
    Called
    2.22
     CALLED
    2.15
     llamado
    2.11
     termed
    2.09
     llamada
    2.00
     chamado
    1.98
     chamada
    1.93
    Activations Density 1.261%

    No Known Activations