© 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. 6588
    Prev
    Next
    INDEX
    Explanations

    references to object creation and data structure initialization in programming contexts

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

    Code initializations using "new."

    np_acts-logits-general · gemini-2.0-flash

    java object creation

    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
    Seq
    -0.47
    ._
    -0.46
     imprimée
    -0.46
     monnaie
    -0.46
    Patience
    -0.46
    transQ
    -0.45
     tillgäng
    -0.43
     verkar
    -0.42
     temporales
    -0.42
     cazul
    -0.42
    POSITIVE LOGITS
    DockStyle
    0.77
    <?
    0.71
     StringTokenizer
    0.65
     doubtnut
    0.63
     estimés
    0.63
     yii
    0.63
     Marquis
    0.61
     Pust
    0.60
    TypedDataSet
    0.60
    ]--;
    0.59
    Activations Density 0.075%

    No Known Activations