© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8177
    Prev
    Next
    INDEX
    Explanations

    geographical names and proper nouns, particularly related to Chinese locations and entities

    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
     насељу
    -0.52
     probate
    -0.49
    ecutable
    -0.49
    TRAILING
    -0.49
    isContained
    -0.48
    IonicModule
    -0.47
     sitter
    -0.47
     Trav
    -0.47
     Assignments
    -0.47
     Administrativna
    -0.46
    POSITIVE LOGITS
    ur
    0.44
    DateFormat
    0.42
    useNewUrlParser
    0.42
    .*")]
    0.40
    Ur
    0.40
     autorytatywna
    0.39
     Ur
    0.38
    ckså
    0.36
    นำ
    0.36
    ("")]
    0.35
    Activations Density 1.441%

    No Known Activations