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. 9-GEMMASCOPE-RES-16K
    6. 15497
    Prev
    Next
    INDEX
    Explanations

    keywords related to cellular growth factors and their roles in biological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    __':
    -0.69
    SourceChecksum
    -0.65
    KommentareTeilen
    -0.59
    InstanceState
    -0.58
     censiti
    -0.57
     auffi
    -0.57
     Epile
    -0.55
     iconLine
    -0.55
     feroit
    -0.55
     vícti
    -0.54
    POSITIVE LOGITS
     cytokines
    0.73
    tokine
    0.65
     secreted
    0.62
     cytokine
    0.60
     Италијани
    0.58
    adaptiveStyles
    0.55
     كومونز
    0.55
    مارات
    0.53
     signaling
    0.53
    bootstrapcdn
    0.51
    Activations Density 1.424%

    No Known Activations