© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9079
    Prev
    Next
    INDEX
    Explanations

    references to research methodologies and data collection processes

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

    Interview-related words

    np_acts-logits-general · gemini-2.0-flash

    interview and interrogation questions

    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
    ServiceProvider
    -0.51
     vœ
    -0.51
     mourned
    -0.49
     Eleg
    -0.46
    providedIn
    -0.45
    AndView
    -0.44
     temporaire
    -0.44
    maat
    -0.43
    hias
    -0.43
     provisoire
    -0.43
    POSITIVE LOGITS
     questions
    1.55
     interviewer
    1.54
     interview
    1.49
     questioning
    1.44
     interrog
    1.44
     interviewing
    1.43
     interrogation
    1.39
     interviewers
    1.36
    interview
    1.31
     Interview
    1.29
    Activations Density 0.585%

    No Known Activations