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. 6442
    Prev
    Next
    INDEX
    Explanations

    words related to deception or manipulation strategies

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

    Follows "been," "is," "was," or "be"

    np_acts-logits-general · gemini-2.0-flash

    verb "to be" followed by states

    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
     works
    -0.47
     ajuns
    -0.47
    processData
    -0.44
    Up
    -0.43
    ContentAsync
    -0.43
     sucedido
    -0.42
     values
    -0.42
     valores
    -0.42
    todoList
    -0.42
     crescimento
    -0.41
    POSITIVE LOGITS
     ActionBar
    0.63
    ()]);
    0.62
    Hauptartikel
    0.62
    Papers
    0.61
    desertcart
    0.60
    spreis
    0.57
     gainera
    0.57
    IntoConstraints
    0.56
    fillType
    0.56
     unknownFields
    0.56
    Activations Density 0.308%

    No Known Activations