© 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. 18-GEMMASCOPE-RES-16K
    11. 370
    Prev
    Next
    INDEX
    Explanations

    conditional statements and control flow constructs in code

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

    Conditional statements ("if", "elif")

    np_acts-logits-general · gemini-2.0-flash

    conditional `if` statements

    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
     hikariConfig
    -0.44
    dib
    -0.43
    Kam
    -0.43
     kam
    -0.42
     ins
    -0.42
    ,...
    -0.42
     !
    -0.41
     close
    -0.41
    gre
    -0.40
     للاسماء
    -0.40
    POSITIVE LOGITS
     مشين
    0.69
     isinstance
    0.68
    IUrlHelper
    0.68
     hasattr
    0.67
    InjectAttribute
    0.66
     '\\;'
    0.64
     houſe
    0.61
     ſtate
    0.61
     helst
    0.61
    jsxFileName
    0.60
    Activations Density 0.196%

    No Known Activations