© 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. 2654
    Prev
    Next
    INDEX
    Explanations

    conditional statements and control flow elements in programming code

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

    Code comparisons and assignments

    np_acts-logits-general · gemini-2.0-flash

    index not found or negative value

    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
    celes
    -0.58
    fjspx
    -0.57
    BeginInit
    -0.56
    RequestMapping
    -0.54
    esModule
    -0.54
     gear
    -0.53
     Ching
    -0.52
    ,:);
    -0.52
     Premi
    -0.51
    Ching
    -0.51
    POSITIVE LOGITS
     invokingState
    0.87
     (-
    0.79
    (-
    0.73
    =-
    0.70
    ==-
    0.66
     $(-
    0.63
    !=-
    0.61
     (−
    0.60
    ADELPHIA
    0.58
     =-
    0.58
    Activations Density 0.249%

    No Known Activations