© 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. 18-GEMMASCOPE-RES-16K
    11. 8391
    Prev
    Next
    INDEX
    Explanations

    statements and phrases related to opinions or assertions about significant topics

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

    preceding clauses or statements

    np_acts-logits-general · gemini-2.0-flash

    if you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -1.02
     légende
    -0.74
     nettoy
    -0.72
     AssemblyCulture
    -0.70
    FieldBuilder
    -0.69
     resourceCulture
    -0.66
    gdx
    -0.66
    MLLoader
    -0.65
    󠁢
    -0.65
     ostavi
    -0.62
    POSITIVE LOGITS
     education
    0.66
     safety
    0.62
     music
    0.57
     sustainability
    0.56
     religion
    0.54
     privacy
    0.54
     teamwork
    0.51
     health
    0.51
    safety
    0.50
     patriotism
    0.49
    Activations Density 0.535%

    No Known Activations