© 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. 2909
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax in programming languages

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

    Tokens followed by the letter "j"

    np_acts-logits-general · gemini-2.0-flash

    j followed by a number or symbol

    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
    raco
    -0.49
    ()',
    -0.48
    ::::::::::::::::
    -0.47
    })));
    -0.47
    ム
    -0.45
    prnewswire
    -0.44
    🇭
    -0.43
    verständlich
    -0.43
    Estado
    -0.43
    webElement
    -0.43
    POSITIVE LOGITS
    J
    0.88
     J
    0.87
    Journal
    0.86
     Journal
    0.84
     job
    0.81
    Job
    0.80
     j
    0.78
    jemahan
    0.78
    Joint
    0.78
     Joint
    0.77
    Activations Density 0.357%

    No Known Activations