© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 2165
    Prev
    Next
    INDEX
    Explanations

    statements that clarify truths against rumors or allegations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    explanation or correction

    np_acts-logits-general · gemini-2.0-flash

    clarification, correction, and rebuttal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.81
    mapStateToProps
    -0.76
    styleable
    -0.71
    abstractmethod
    -0.70
    RTEX
    -0.69
    usermodel
    -0.68
     HasFactory
    -0.67
    ngrx
    -0.67
    
    -0.66
    ########.
    -0.65
    POSITIVE LOGITS
     clarification
    1.18
     aclar
    1.09
     clarifying
    1.07
     clarify
    1.05
     clarified
    1.00
     aclarar
    1.00
     clarifies
    0.99
     explanation
    0.87
     rebuttal
    0.85
    澄
    0.84
    Activations Density 0.370%

    No Known Activations