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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9165
    Prev
    Next
    INDEX
    Explanations

    code structure components and their definitions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entyfik
    -0.61
    awtextra
    -0.58
    InvalidProtocol
    -0.52
    ThroughAttribute
    -0.51
    الحياه
    -0.50
    principalTable
    -0.50
    iprot
    -0.50
     utafitiHapana
    -0.49
    HasAnnotation
    -0.48
     Wern
    -0.46
    POSITIVE LOGITS
     _('
    0.69
    клопе
    0.68
    PhysRevLett
    0.65
     %>%
    0.63
    '&:
    0.63
     _("
    0.63
    Datuak
    0.62
     def
    0.61
    Jährige
    0.61
    })->
    0.61
    Activations Density 0.047%

    No Known Activations