© 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. 20-GEMMASCOPE-RES-16K
    11. 5938
    Prev
    Next
    INDEX
    Explanations

    instances of discussing inappropriate or negative comments about others, especially in a professional context

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

    speaking, reading, or occurring in public

    np_acts-logits-general · gemini-2.0-flash

    in front of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Autorisations
    -0.74
     للاسماء
    -0.72
    principalTable
    -0.72
     ujednoznacz
    -0.68
     متعلقه
    -0.68
    IVEREF
    -0.64
     विश्वसनीयता
    -0.64
     ExecuteAsync
    -0.63
    IntoConstraints
    -0.63
    //});
    -0.61
    POSITIVE LOGITS
     devant
    1.52
     أمام
    1.39
     publicly
    1.38
     delante
    1.31
     davanti
    1.30
     public
    1.29
     frente
    1.16
    public
    1.11
     hadapan
    1.07
     PUBLIC
    1.04
    Activations Density 0.300%

    No Known Activations