© 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. 5-GEMMASCOPE-RES-16K
    11. 10844
    Prev
    Next
    INDEX
    Explanations

    references to oil and related substances or topics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     presencial
    -0.68
    ByExample
    -0.66
     CSC
    -0.63
    )++;
    -0.62
    culata
    -0.61
    ztes
    -0.60
    ++++++++++++++++
    -0.59
     besti
    -0.59
     Γ
    -0.59
     menti
    -0.59
    POSITIVE LOGITS
     oil
    2.57
     Oil
    2.52
     OIL
    2.44
    Oil
    2.35
    oil
    2.31
     oils
    2.28
     Oils
    2.22
    OIL
    2.15
    油
    1.71
     olie
    1.64
    Activations Density 0.032%

    No Known Activations