© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4592
    Prev
    Next
    INDEX
    Explanations

    mentions of surveys and questionnaires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bentar
    -0.46
    зулта
    -0.43
    ########.
    -0.41
    angeran
    -0.40
    Aktualisiert
    -0.40
    SocketAddress
    -0.40
    ceptre
    -0.40
     AssemblyCompany
    -0.39
    ="@+
    -0.39
    abestanden
    -0.38
    POSITIVE LOGITS
     survey
    3.94
     Survey
    3.55
     surveys
    3.39
    Survey
    3.36
    survey
    3.30
     SURVEY
    3.20
     Surveys
    3.14
    Surveys
    2.89
     surveyed
    2.81
    surveys
    2.73
    Activations Density 0.148%

    No Known Activations