© 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. 10558
    Prev
    Next
    INDEX
    Explanations

    information related to personal achievements and educational background

    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
    WriteTagHelper
    -0.48
     poni
    -0.44
    编
    -0.43
     matters
    -0.40
     face
    -0.40
     post
    -0.39
    AndEndTag
    -0.39
    Jeografia
    -0.39
     su
    -0.38
     expectations
    -0.38
    POSITIVE LOGITS
    extAlignment
    0.77
     ویکی‌پدیای
    0.77
    Obrázky
    0.76
    ContentAlignment
    0.75
    Tikang
    0.74
    Parcelize
    0.73
     sumpay
    0.68
    Pratique
    0.66
    ">—
    0.64
    AutoScaleMode
    0.63
    Activations Density 0.311%

    No Known Activations