© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3245
    Prev
    Next
    INDEX
    Explanations

    references to physical properties and characteristics of objects or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gre
    -0.48
     high
    -0.47
    od
    -0.47
    cy
    -0.46
    ırl
    -0.46
    ential
    -0.45
    has
    -0.44
    gett
    -0.42
    dze
    -0.42
    '
    -0.42
    POSITIVE LOGITS
    TypedDataSet
    0.79
     itſelf
    0.77
    ConstraintMaker
    0.73
    ſelves
    0.69
    ſelf
    0.68
    IntoConstraints
    0.67
    WindowConstants
    0.66
     whoſe
    0.66
    afficheront
    0.66
     CreateTagHelper
    0.65
    Activations Density 0.777%

    No Known Activations