© 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. 25-GEMMASCOPE-RES-16K
    11. 4672
    Prev
    Next
    INDEX
    Explanations

    references to prohibited practices or actions related to accounting and financial conduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.74
    sbereich
    -0.56
     agujero
    -0.53
     igång
    -0.53
    onAttach
    -0.51
    relsen
    -0.49
    ZoneId
    -0.49
    updateUI
    -0.48
     inversa
    -0.48
    teknik
    -0.48
    POSITIVE LOGITS
    shoot
    0.90
    beat
    0.81
    loading
    0.78
    springs
    0.75
     kil
    0.73
    loaded
    0.73
    handedly
    0.72
     limits
    0.71
    sho
    0.71
    screen
    0.71
    Activations Density 0.098%

    No Known Activations