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. 8482
    Prev
    Next
    INDEX
    Explanations

    expressions of pride and commitment to cultural or artistic endeavors

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

    Follows titles, names, or quotes

    np_acts-logits-general · gemini-2.0-flash

    shows to watch

    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
    IsContent
    -0.92
     purpoſe
    -0.89
     Efq
    -0.87
     Theſe
    -0.84
     CreateTagHelper
    -0.83
     raiſ
    -0.81
     Reſ
    -0.80
     reaſon
    -0.80
     ſtate
    -0.80
     ſeveral
    -0.80
    POSITIVE LOGITS
    webElementXpaths
    0.54
     Mr
    0.51
    Mr
    0.49
    ByExample
    0.46
    Ms
    0.46
    awaiter
    0.44
     Acting
    0.43
     mouseClicked
    0.42
     Ms
    0.42
     acting
    0.42
    Activations Density 0.067%

    No Known Activations