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-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9204
    Prev
    Next
    INDEX
    Explanations

    concepts related to research methods and data collection in studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.63
     MainAxisSize
    -0.54
     ujednoznacz
    -0.52
    DockStyle
    -0.52
    AddTagHelper
    -0.50
    tagPool
    -0.46
     nakalista
    -0.46
     disambiguazione
    -0.44
     صوتيه
    -0.43
    这家伙
    -0.43
    POSITIVE LOGITS
     survey
    0.76
     interviews
    0.71
     interviewing
    0.69
     questionnaire
    0.68
     questionnaires
    0.67
     surveys
    0.66
     interview
    0.64
     sampling
    0.64
     Survey
    0.63
     respondent
    0.60
    Activations Density 0.935%

    No Known Activations