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. 21-GEMMASCOPE-RES-16K
    6. 7262
    Prev
    Next
    INDEX
    Explanations

    mentions of video game analysis

    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
    delwed
    -0.43
    IBOutlet
    -0.42
     médaille
    -0.41
    edipus
    -0.40
    солю
    -0.40
    writeFieldEnd
    -0.40
    IBAction
    -0.40
     HomeController
    -0.38
    Filmographie
    -0.38
    künfte
    -0.38
    POSITIVE LOGITS
     fandom
    0.61
     snob
    0.52
    fans
    0.49
     aficionados
    0.49
     dissect
    0.47
     fan
    0.47
     analysing
    0.45
     analyses
    0.45
     sexism
    0.45
     fanatic
    0.45
    Activations Density 0.328%

    No Known Activations