© 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. 37-GEMMASCOPE-RES-16K
    11. 3909
    Prev
    Next
    INDEX
    Explanations

    references to political power struggles and interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.62
    richTextPanel
    -0.59
    UpInside
    -0.58
     незавершена
    -0.55
     tričko
    -0.49
     gynhyrchwyd
    -0.49
     ainfi
    -0.47
    }{*}{
    -0.47
     zoude
    -0.46
     sân
    -0.45
    POSITIVE LOGITS
    esModule
    0.49
    SpringRunner
    0.45
     Aryan
    0.44
    caux
    0.44
    OGND
    0.43
    fiche
    0.40
    ★★★★☆
    0.39
    PostMapping
    0.39
    ètres
    0.39
    出版年
    0.39
    Activations Density 1.032%

    No Known Activations