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. 22-GEMMASCOPE-RES-16K
    6. 5849
    Prev
    Next
    INDEX
    Explanations

    elements related to method definitions and their accessibility in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Protobuf-related code or data structures

    np_acts-logits-general · gemini-2.0-flash

    tokens after activation are return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.79
    ThroughAttribute
    -0.74
     FetchType
    -0.72
    mybatisplus
    -0.71
     ExecuteAsync
    -0.64
    IntoConstraints
    -0.63
    featureID
    -0.62
    ItemBackground
    -0.62
     المعيارى
    -0.61
     الدولى
    -0.61
    POSITIVE LOGITS
     ModelExpression
    0.56
    InjectAttribute
    0.51
    __':
    
    0.50
     Normdatei
    0.47
    "))
    
    0.46
    __":
    
    0.46
     worker
    0.45
    OGND
    0.44
    Vidite
    0.44
    жели
    0.43
    Activations Density 0.132%

    No Known Activations