Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 724
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "ArrayList" and its related constructs in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bind
    -0.69
     bindings
    -0.68
     Sel
    -0.65
    Sel
    -0.62
    HasOne
    -0.61
    Honours
    -0.61
    Demografia
    -0.60
    Bindings
    -0.58
    Redacción
    -0.57
    Nuorodos
    -0.57
    POSITIVE LOGITS
     ArrayList
    1.40
    ArrayList
    1.39
     arrayList
    0.94
    newArrayList
    0.85
    arrayList
    0.81
     Allie
    0.59
     Gators
    0.57
    Filmografie
    0.55
     CURIAM
    0.55
    umbledore
    0.55
    Activations Density 0.011%

    No Known Activations