© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12442
    Prev
    Next
    INDEX
    Explanations

    requests for information regarding an exam process

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

    after specific academic terms

    np_acts-logits-general · gemini-2.0-flash

    Category: education or diploma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyrchwyd
    -0.56
     duele
    -0.49
    PYX
    -0.45
    ValueStyle
    -0.45
     pemimpin
    -0.44
    UnitTesting
    -0.44
     Weisheit
    -0.43
     liderazgo
    -0.43
     AssemblyCulture
    -0.42
    colgante
    -0.41
    POSITIVE LOGITS
     hostel
    0.46
     absc
    0.41
     arre
    0.41
     hostels
    0.40
     $_[
    0.40
    Hostel
    0.40
    rungsseite
    0.39
     Practical
    0.39
     subjects
    0.38
     compulsory
    0.37
    Activations Density 0.078%

    No Known Activations