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. 4-GEMMASCOPE-RES-16K
    6. 3647
    Prev
    Next
    INDEX
    Explanations

    HTML tag attributes and their respective values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ffron
    -0.61
    Ehrungen
    -0.61
     hru
    -0.60
    ViewInit
    -0.57
    TestingModule
    -0.56
    NewLabel
    -0.55
    mbals
    -0.55
     SEDS
    -0.55
     AppBar
    -0.54
    losseum
    -0.54
    POSITIVE LOGITS
     getType
    0.94
     Type
    0.82
     TYPE
    0.80
     setType
    0.75
    ècie
    0.70
     Types
    0.70
    TYPE
    0.69
     types
    0.68
     виправивши
    0.68
    getType
    0.67
    Activations Density 0.281%

    No Known Activations