© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 407
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationships or connections, particularly those starting with "from which"

    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
    IsPostBack
    -0.83
    StoreMessageInfo
    -0.68
    Obrázky
    -0.67
     viewDidLoad
    -0.62
    duled
    -0.62
    RenderAtEndOf
    -0.60
    сник
    -0.58
     HasFactory
    -0.58
    stuhl
    -0.58
    rrggbb
    -0.58
    POSITIVE LOGITS
    FROM
    1.05
    From
    1.03
     therefrom
    1.03
     From
    0.97
     FROM
    0.97
    from
    0.96
     whence
    0.91
     Whence
    0.91
     from
    0.83
    から
    0.83
    Activations Density 0.160%

    No Known Activations