Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 7055
    Prev
    Next
    INDEX
    Explanations

    mathematical or physical propositions and their contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.57
    GEBURTSDATUM
    -0.55
    发表于
    -0.54
     Taktlose
    -0.54
     ब्रेकडाउन
    -0.53
    تقاوى
    -0.52
    RenderAtEndOf
    -0.51
    Хьажоргаш
    -0.50
     kasarigan
    -0.50
    EndProject
    -0.50
    POSITIVE LOGITS
    msgTypes
    0.47
     proceeding
    0.45
    stateMutability
    0.42
    ########.
    0.42
     TextAlign
    0.41
     falling
    0.40
     boo
    0.38
    HttpStatusCode
    0.36
     tuần
    0.36
     nok
    0.36
    Activations Density 0.946%

    No Known Activations