© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9667
    Prev
    Next
    INDEX
    Explanations

    references to editions and publications of various works

    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
    Kapcsolódó
    -0.45
    ooga
    -0.43
     leña
    -0.43
    rimas
    -0.43
    oa̍t
    -0.42
    })));
    -0.41
    OneToMany
    -0.41
    kozá
    -0.41
    ミナル
    -0.40
    なり
    -0.40
    POSITIVE LOGITS
     version
    0.92
     versions
    0.89
     snippetHide
    0.81
     VERSION
    0.79
     Versions
    0.77
     versione
    0.76
    AndEndTag
    0.74
    ніципа
    0.73
     versão
    0.71
     versión
    0.70
    Activations Density 0.643%

    No Known Activations