© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2536
    Prev
    Next
    INDEX
    Explanations

    elements related to object-oriented programming constructs, particularly method calls and their parameters

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

    Method calls (often "get" methods)

    np_acts-logits-general · gemini-2.0-flash

    method calls in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setMessage
    -0.79
     setCode
    -0.77
     setType
    -0.76
    featureID
    -0.73
     setStatus
    -0.73
     setTime
    -0.72
     setAddress
    -0.69
     packageName
    -0.65
     imagePath
    -0.64
     memberId
    -0.64
    POSITIVE LOGITS
    get
    0.50
     meille
    0.47
     aikaa
    0.44
    urably
    0.41
     enää
    0.41
    entially
    0.40
     florales
    0.40
     '\\;'
    0.39
     intStringLen
    0.39
    četně
    0.39
    Activations Density 0.210%

    No Known Activations