© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12374
    Prev
    Next
    INDEX
    Explanations

    expressions of personal belief or opinion

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

    Follows personal pronouns and related words

    np_acts-logits-general · gemini-2.0-flash

    expressing opinions or assessments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apparently
    -0.70
     aparentemente
    -0.68
     seemingly
    -0.68
     schein
    -0.63
    apparently
    -0.61
     Apparently
    -0.60
     nicht
    -0.56
    parently
    -0.55
    Apparently
    -0.54
     Seem
    -0.53
    POSITIVE LOGITS
     fairest
    0.53
     unfairly
    0.48
     pretty
    0.48
     fair
    0.46
     underrated
    0.45
     fairer
    0.45
     deserve
    0.42
     overrated
    0.42
     fairly
    0.41
     mérit
    0.40
    Activations Density 0.312%

    No Known Activations