© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 15711
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate opportunities and potential actions or outcomes in various contexts

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

    capitalizing or taking advantage of opportunities

    np_acts-logits-general · gemini-2.0-flash

    to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.71
    ctos
    -0.47
    bujete
    -0.46
     plantel
    -0.45
     Scritto
    -0.44
    govina
    -0.43
    acquisto
    -0.42
    Externé
    -0.42
     препратки
    -0.42
    EditorBrowsable
    -0.41
    POSITIVE LOGITS
     capitalize
    1.86
     capital
    1.76
     capitalized
    1.72
     benefit
    1.65
     aprovechar
    1.55
     benefited
    1.52
     exploit
    1.51
    Benefit
    1.50
    benefit
    1.46
     benefitted
    1.46
    Activations Density 0.362%

    No Known Activations