© 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. 22-GEMMASCOPE-RES-16K
    11. 5659
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data types, particularly related to variable declarations and control structures

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

    "int i" or loop indices

    np_acts-logits-general · gemini-2.0-flash

    int i loop initialization

    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
     Wicidata
    -0.77
     disambiguazione
    -0.69
    rawDesc
    -0.65
    MessageOf
    -0.65
     חיצוניים
    -0.64
    =$?
    -0.64
     الوطنيه
    -0.61
    Portale
    -0.61
     bpy
    -0.59
     Administrativna
    -0.58
    POSITIVE LOGITS
     j
    1.04
     i
    0.84
     ii
    0.79
     k
    0.78
     counter
    0.69
    j
    0.69
     iter
    0.65
    counter
    0.63
    ii
    0.61
    Counter
    0.61
    Activations Density 0.117%

    No Known Activations