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. 6-GEMMASCOPE-RES-16K
    6. 12114
    Prev
    Next
    INDEX
    Explanations

    references to uniformity or uniform distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wisata
    -0.83
    ########.
    -0.83
     useContext
    -0.82
     henvisninger
    -0.78
     ControllerBase
    -0.75
    WAUKEE
    -0.74
    ValueStyle
    -0.74
     Juga
    -0.72
    RuleContext
    -0.72
    PhysRevLett
    -0.72
    POSITIVE LOGITS
     uniform
    1.70
    Uniform
    1.63
    uniform
    1.62
     Uniform
    1.59
     uniforms
    1.46
     uniformity
    1.40
    IFORM
    1.32
    iforms
    1.28
     uniformes
    1.27
     uniforme
    1.22
    Activations Density 0.116%

    No Known Activations