© 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. 8-GEMMASCOPE-RES-16K
    11. 13609
    Prev
    Next
    INDEX
    Explanations

    terms related to bending or flexibility, particularly in physical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seeder
    -0.76
    ريكا
    -0.68
    esez
    -0.67
    GEBURTSDATUM
    -0.65
    BeginContext
    -0.65
    savefig
    -0.63
    uffer
    -0.61
     bőr
    -0.60
     poitrine
    -0.59
    Datuak
    -0.59
    POSITIVE LOGITS
     bending
    1.48
     bent
    1.33
     Bending
    1.32
     bend
    1.31
     bends
    1.28
    bend
    1.25
    Bent
    1.22
    Bend
    1.18
     Bent
    1.18
     Bend
    1.13
    Activations Density 0.295%

    No Known Activations