© 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 EvalsExportsinterp-engineNEWAPI 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. 6809
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or involvement of any entity or group

    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
    UrlEncoded
    -0.62
     ред
    -0.53
    NI
    -0.51
    PLAUSE
    -0.51
    fml
    -0.48
     very
    -0.46
    ZI
    -0.46
     cref
    -0.45
    ั้ง
    -0.45
    sunami
    -0.45
    POSITIVE LOGITS
     anybody
    1.38
     apapun
    1.37
     anyone
    1.34
     Any
    1.33
    Any
    1.31
     Anybody
    1.29
     any
    1.28
     ANY
    1.26
    anything
    1.26
     Cualquier
    1.26
    Activations Density 0.285%

    No Known Activations