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. 7982
    Prev
    Next
    INDEX
    Explanations

    references to libraries or frameworks 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
    enumi
    -1.25
    SequentialGroup
    -0.85
    "</
    -0.84
     TextInputType
    -0.84
    enumii
    -0.84
     IndexPath
    -0.81
    ).</
    -0.81
    migrationBuilder
    -0.80
    EndInit
    -0.78
    DataAnnotations
    -0.78
    POSITIVE LOGITS
    NgModule
    0.73
    HasColumnType
    0.66
    rungsseite
    0.63
    الدراسه
    0.62
    NameInMap
    0.55
    justifyContent
    0.55
    HasBeenSet
    0.55
     jadx
    0.55
    ModelBuilder
    0.54
    Rüyada
    0.51
    Activations Density 0.003%

    No Known Activations