Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10461
    Prev
    Next
    INDEX
    Explanations

    references to confidence and self-assurance

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

    Pronouns followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    pronoun followed by verb

    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
    Personensuche
    -0.76
    IntoConstraints
    -0.59
     officiating
    -0.52
     femen
    -0.51
     sighing
    -0.50
    testify
    -0.49
     centenary
    -0.49
    
    -0.48
     scrambling
    -0.48
     grading
    -0.48
    POSITIVE LOGITS
     is
    1.13
     can
    1.07
     has
    1.05
     was
    0.99
     will
    0.94
     actually
    0.93
     had
    0.88
     have
    0.87
     cannot
    0.85
     could
    0.84
    Activations Density 1.145%

    No Known Activations