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. 18-GEMMASCOPE-RES-16K
    6. 8246
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "across."

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

    "across"

    np_acts-logits-general · gemini-2.0-flash

    across the

    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
    Anhalt
    -0.75
     ролях
    -0.63
    HasAnnotation
    -0.61
     ListNode
    -0.60
    DebuggerStep
    -0.59
    manuel
    -0.59
    ophilus
    -0.59
     exclusivas
    -0.59
     idéia
    -0.58
     igång
    -0.58
    POSITIVE LOGITS
     ACROSS
    0.98
     across
    0.98
     Across
    0.92
    across
    0.91
    Across
    0.89
     crossed
    0.83
     Crossing
    0.79
     crosses
    0.78
     crossing
    0.77
    Crossing
    0.76
    Activations Density 0.045%

    No Known Activations