© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 9348
    Prev
    Next
    INDEX
    Explanations

    references to ambiguous terms and their variations related to scientific terminology

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

    starting with "Amb" or containing "Amb"

    np_acts-logits-general · gemini-2.0-flash

    amb followed by endings

    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
    MessageOf
    -0.75
    styleUrls
    -0.73
     BehaviorSubject
    -0.71
    lacian
    -0.66
    ReusableCell
    -0.65
     Wikimedijinoj
    -0.65
    >-->
    -0.64
     nonUne
    -0.64
    expandindo
    -0.64
     métiers
    -0.63
    POSITIVE LOGITS
     Ambro
    1.02
     Amb
    0.92
    amb
    0.92
     amb
    0.85
    Amb
    0.84
    AMB
    0.83
     amp
    0.81
     EMB
    0.81
     Jamb
    0.79
     Imb
    0.77
    Activations Density 0.332%

    No Known Activations