© 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. 14-GEMMASCOPE-RES-16K
    6. 7825
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "total" and its related derivatives indicating cumulative statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ethene
    -0.65
    ccb
    -0.63
    Kaynakça
    -0.61
    Архівовано
    -0.58
    skis
    -0.57
     rekomendasi
    -0.57
     gibi
    -0.55
     Mercurio
    -0.54
    ']?>
    -0.54
    dengar
    -0.53
    POSITIVE LOGITS
     totals
    1.15
     Totals
    1.10
     getTotal
    1.10
     TOTAL
    1.07
    TOTAL
    1.06
     total
    1.05
     tota
    1.04
    tổng
    1.01
     setTotal
    0.99
    setTotal
    0.98
    Activations Density 0.040%

    No Known Activations