© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 11932
    Prev
    Next
    INDEX
    Explanations

    mentions of audience engagement and feedback responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.51
    ngrx
    -0.51
    出版年
    -0.51
     ComVisible
    -0.48
     ThemeData
    -0.44
    __":
    -0.44
    liferay
    -0.40
    TemporalType
    -0.40
     NgModule
    -0.38
    IntoConstraints
    -0.38
    POSITIVE LOGITS
     feedback
    1.51
     responses
    1.28
     reacties
    1.26
    feedback
    1.25
     Feedback
    1.24
     feedbacks
    1.22
     response
    1.21
    Feedback
    1.20
     reactions
    1.16
     demand
    1.12
    Activations Density 0.489%

    No Known Activations