© 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. 4-GEMMASCOPE-RES-16K
    6. 12659
    Prev
    Next
    INDEX
    Explanations

    terms related to concentration and dosage 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 @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.72
    …"
    -0.69
    ัติ
    -0.65
    marvin
    -0.62
    WindowListener
    -0.62
    Duración
    -0.62
    wied
    -0.61
    او
    -0.61
    beau
    -0.61
     επισ
    -0.60
    POSITIVE LOGITS
     concentration
    2.43
     Concentration
    2.42
     concentrations
    2.26
    concentration
    2.18
     Concentrations
    2.16
     CONCENT
    2.14
    Concentration
    2.13
    concentr
    1.86
    Concentr
    1.83
     Concentr
    1.71
    Activations Density 0.111%

    No Known Activations