© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 7000
    Prev
    Next
    INDEX
    Explanations

    names of individuals and familial relationships

    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
    ResumeLayout
    -0.44
    üyada
    -0.42
    putan
    -0.42
     taut
    -0.40
    zeera
    -0.40
     كورة
    -0.39
    ウンジ
    -0.38
     aandacht
    -0.38
    ble
    -0.38
    MOUTH
    -0.38
    POSITIVE LOGITS
    ⟬
    0.56
    Rhestr
    0.44
    InjectAttribute
    0.43
     branche
    0.41
    disposing
    0.41
     Houſe
    0.41
     Perſ
    0.41
     juſ
    0.40
     Momente
    0.39
     diagon
    0.38
    Activations Density 0.269%

    No Known Activations