© 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. 4666
    Prev
    Next
    INDEX
    Explanations

    questions and answers related to financial and lending topics

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

    Sentences ending with "."

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and transitions

    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
    是我的
    -0.77
    XmlAccessType
    -0.66
    Билгалдахарш
    -0.60
    )("
    -0.58
    —“
    -0.58
    GOTREF
    -0.58
     MINE
    -0.57
    MINE
    -0.56
    fromnode
    -0.55
     mine
    -0.55
    POSITIVE LOGITS
     Moreover
    1.22
    Moreover
    1.20
     Apart
    1.12
    Apart
    1.12
     Hence
    1.05
     moreover
    1.04
     besides
    1.01
     Besides
    1.00
    Hence
    0.99
     thus
    0.96
    Activations Density 0.078%

    No Known Activations