© 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. 10-GEMMASCOPE-RES-16K
    11. 11035
    Prev
    Next
    INDEX
    Explanations

    qualifiers indicating slight differences or variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сю
    -0.56
    conn
    -0.56
    Mang
    -0.56
    Externí
    -0.55
    kal
    -0.55
    Dữ
    -0.53
    AutoScaleMode
    -0.53
    portál
    -0.53
    いかに
    -0.53
    łac
    -0.52
    POSITIVE LOGITS
    Slightly
    1.17
    slightly
    1.14
     slightly
    1.10
     Slightly
    1.08
     Etwas
    1.05
    Slight
    1.01
     کمی
    0.99
     légèrement
    0.98
    Somewhat
    0.96
     nieco
    0.95
    Activations Density 0.164%

    No Known Activations