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. 7-GEMMASCOPE-RES-16K
    6. 4531
    Prev
    Next
    INDEX
    Explanations

    characters and symbols used in programming syntax and data structure definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kels
    -0.57
    ngOnInit
    -0.56
    เหน
    -0.54
     thoát
    -0.52
    clable
    -0.52
     sometimes
    -0.52
     counter
    -0.50
    isons
    -0.50
    osoma
    -0.49
     dysfunction
    -0.49
    POSITIVE LOGITS
    ImageContext
    0.84
    [:
    0.82
    +#+#
    0.81
    DockStyle
    0.73
     المعيارى
    0.72
    :][
    0.71
    numerusform
    0.68
    TemporalType
    0.67
     métallique
    0.64
     uska
    0.63
    Activations Density 0.113%

    No Known Activations