© 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. 24-GEMMASCOPE-RES-16K
    6. 4652
    Prev
    Next
    INDEX
    Explanations

    expressions of dissatisfaction or negative reviews

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

    Negative sentiment after a conjunction or period

    np_acts-logits-general · gemini-2.0-flash

    negative sentiment or bad quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -0.76
    enderror
    -0.76
    ConstraintMaker
    -0.72
    LayoutConstraint
    -0.71
     imageNamed
    -0.66
    嘿嘿
    -0.64
     validamos
    -0.63
    Hehe
    -0.62
     ^_^
    -0.62
    VersionUID
    -0.62
    POSITIVE LOGITS
     Terrible
    1.02
    Terrible
    0.96
     terrible
    0.94
    Awful
    0.94
     Worse
    0.92
    Worse
    0.91
     AVOID
    0.89
     horrible
    0.87
     worst
    0.87
     Worst
    0.86
    Activations Density 0.085%

    No Known Activations