© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14070
    Prev
    Next
    INDEX
    Explanations

    function calls related to output operations in programming

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

    C-related code (printf, fprintf)

    np_acts-logits-general · gemini-2.0-flash

    C code output format strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ρίου
    -0.57
    kháu
    -0.53
    драт
    -0.50
     Himo
    -0.49
    WithIOException
    -0.48
     africana
    -0.48
    Архівовано
    -0.47
     तो
    -0.46
    elemField
    -0.45
    oa̍t
    -0.45
    POSITIVE LOGITS
    stdio
    0.80
    jsonwebtoken
    0.60
     rospy
    0.59
    createQuery
    0.59
    Hochspringen
    0.55
    ########.
    0.54
     portée
    0.53
     argc
    0.53
     useContext
    0.52
     Mathi
    0.52
    Activations Density 0.156%

    No Known Activations