© 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. 3-GEMMASCOPE-RES-16K
    11. 4890
    Prev
    Next
    INDEX
    Explanations

    references to specific temporal markers, particularly the phrase "at this point."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.61
    الحياه
    -0.53
    ########.
    -0.49
     مرئيه
    -0.47
    providedIn
    -0.47
    StoryboardSegue
    -0.47
    "}")
    -0.47
    rawDesc
    -0.47
    sonaro
    -0.45
     الحره
    -0.45
    POSITIVE LOGITS
    yntaxException
    0.39
     imaginary
    0.38
    vább
    0.36
     spē
    0.36
    FieldBuilder
    0.35
    yarnpkg
    0.34
    也不敢
    0.34
     φυσ
    0.34
    stateParams
    0.34
     official
    0.33
    Activations Density 0.160%

    No Known Activations