© 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. 8252
    Prev
    Next
    INDEX
    Explanations

    terms related to correctness and incorrectness

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

    "Correct" and "wrong" labels or predictions

    np_acts-logits-general · gemini-2.0-flash

    correct or wrong assessments

    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
     AssemblyCompany
    -0.88
    tagHelperRunner
    -0.79
     ostavi
    -0.75
     newBuilder
    -0.74
     المعيارى
    -0.71
    InitVars
    -0.69
    +#+#
    -0.69
    awaiter
    -0.69
    InjectAttribute
    -0.68
     كومونز
    -0.68
    POSITIVE LOGITS
     Wrong
    0.89
    Wrong
    0.78
     wrong
    0.78
     错误
    0.76
     Incorrect
    0.76
     WRONG
    0.76
     wrongs
    0.74
    WRONG
    0.74
     incorrect
    0.72
    wrong
    0.72
    Activations Density 0.200%

    No Known Activations