© 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. 15-GEMMASCOPE-RES-16K
    11. 5374
    Prev
    Next
    INDEX
    Explanations

    terms related to interpreting data and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Obl
    -0.55
     oublié
    -0.54
    プーン
    -0.52
    rolid
    -0.50
    rekli
    -0.50
    #+#
    -0.49
     moelle
    -0.48
    hilangan
    -0.48
    gridx
    -0.48
    GetEnumerator
    -0.47
    POSITIVE LOGITS
    Interpret
    1.06
     interpre
    1.05
     interprets
    1.04
     interpreting
    1.03
     interpret
    1.02
     INTERPRET
    1.00
     interpretar
    0.97
     interpretations
    0.94
    interpre
    0.93
     interpreta
    0.91
    Activations Density 0.434%

    No Known Activations