© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12708
    Prev
    Next
    INDEX
    Explanations

    Java class definitions and method invocations, particularly in the context of Android development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addGap
    -1.21
    addPreferredGap
    -0.75
     OnInit
    -0.63
    addContainerGap
    -0.47
    amssymb
    -0.40
    MathML
    -0.39
     subtilis
    -0.35
     Heal
    -0.35
    Фар
    -0.34
     heal
    -0.34
    POSITIVE LOGITS
    WEBPACK
    2.20
    SequentialGroup
    1.51
     onCreate
    1.37
    onCreate
    1.25
     javafx
    1.02
     onCreateView
    1.01
    ScopeManager
    0.99
    junit
    0.98
    setContentView
    0.91
    Slf
    0.80
    Activations Density 0.014%

    No Known Activations