© 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. 33-GEMMASCOPE-RES-16K
    11. 292
    Prev
    Next
    INDEX
    Explanations

    specific academic or professional titles and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.63
    AndEndTag
    -0.63
    AnchorStyles
    -0.53
     disambiguazione
    -0.51
     CreateTagHelper
    -0.50
    LookAnd
    -0.49
    __);
    -0.48
    verwijspagina
    -0.47
    ɵɵelementStart
    -0.46
     Audiodateien
    -0.45
    POSITIVE LOGITS
     recipients
    1.65
     recipient
    1.57
     beneficiaries
    1.43
     Recipients
    1.36
     winners
    1.30
     winner
    1.28
     beneficiary
    1.27
     Recipient
    1.25
     participants
    1.24
     candidates
    1.24
    Activations Density 0.952%

    No Known Activations