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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11749
    Prev
    Next
    INDEX
    Explanations

    references to memorials and tributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chriftian
    -0.60
    MLLoader
    -0.60
    amazonaws
    -0.49
     chrétien
    -0.48
    zzleHttp
    -0.47
    awtextra
    -0.46
    googleapis
    -0.46
    FontOfSize
    -0.45
     Eſ
    -0.45
     chrétiens
    -0.44
    POSITIVE LOGITS
     memorial
    0.63
    AnchorStyles
    0.60
     anniversary
    0.58
     monument
    0.56
     honoring
    0.55
     MEMORIAL
    0.55
    ITAGE
    0.54
    Memorial
    0.54
     keepsake
    0.54
    纪念
    0.53
    Activations Density 0.473%

    No Known Activations