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. 16-GEMMASCOPE-RES-16K
    6. 342
    Prev
    Next
    INDEX
    Explanations

    Java method declarations and overrides in class definitions

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

    "void" keyword followed by "on" or "run"

    np_acts-logits-general · gemini-2.0-flash

    creating runnable/anonymous methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stridium
    -0.54
    Hands
    -0.49
    tso
    -0.45
    Curly
    -0.44
    ்த்த
    -0.44
    埋
    -0.42
    RefNanny
    -0.42
     Hands
    -0.42
    wnia
    -0.41
    unct
    -0.40
    POSITIVE LOGITS
    matchCondition
    0.78
    Datuak
    0.74
    wpi
    0.71
    Hentet
    0.71
    principalTable
    0.69
    RectangleBorder
    0.68
    OGND
    0.67
    archiviato
    0.66
    '])->
    0.65
     kasarigan
    0.64
    Activations Density 0.156%

    No Known Activations