© 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. 4-GEMMASCOPE-RES-16K
    6. 2974
    Prev
    Next
    INDEX
    Explanations

    features and components related to vehicle systems and their controls

    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
     dzięki
    -0.48
    ⓧ
    -0.45
     tomber
    -0.45
     urma
    -0.45
    равда
    -0.44
    varargin
    -0.43
    QtCore
    -0.43
    idation
    -0.43
    zige
    -0.42
    jahtera
    -0.42
    POSITIVE LOGITS
     steering
    0.91
     wipers
    0.79
     المعيارى
    0.77
     Steering
    0.73
    steering
    0.73
     Chwiliwch
    0.72
     chofe
    0.71
    Steering
    0.71
    MethodManager
    0.70
     للاسماء
    0.69
    Activations Density 0.826%

    No Known Activations