© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 12923
    Prev
    Next
    INDEX
    Explanations

    phrases indicating completion or discovery of information

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

    Past tense verbs indicating discovery or completion

    np_acts-logits-general · gemini-2.0-flash

    conclusion reached

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anstalt
    -0.29
    닌
    -0.26
     continuous
    -0.26
     durée
    -0.26
     vorkommen
    -0.25
     C
    -0.25
     val
    -0.23
     ge
    -0.23
    ↵↵
    -0.22
     si
    -0.22
    POSITIVE LOGITS
    ArgsConstructor
    0.82
     témoig
    0.81
     queſta
    0.81
     wireType
    0.79
     مشين
    0.79
     パンチラ
    0.78
    arangay
    0.78
     ModelExpression
    0.78
    <unused52>
    0.76
    <unused8>
    0.75
    Activations Density 0.843%

    No Known Activations