© 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. 13804
    Prev
    Next
    INDEX
    Explanations

    assignment statements or expressions in code

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

    Boolean values and assignments

    np_acts-logits-general · gemini-2.0-flash

    boolean true

    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
    
    -0.80
    SourceChecksum
    -0.77
     mergeFrom
    -0.65
    ">—
    -0.64
    protoimpl
    -0.62
    riwal
    -0.61
    ReusableCell
    -0.61
     HasFactory
    -0.59
    DockStyle
    -0.58
    parsedMessage
    -0.58
    POSITIVE LOGITS
     true
    2.43
    true
    2.17
     True
    1.57
     TRUE
    1.53
    True
    1.51
    TRUE
    1.39
     vrai
    1.33
     verdadero
    1.29
     verdadeiro
    1.24
     verdadera
    1.24
    Activations Density 0.081%

    No Known Activations