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

    Neuronpedia

    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. 0-GEMMASCOPE-RES-16K
    11. 6161
    Prev
    Next
    INDEX
    Explanations

    terms related to requirements and selections in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -0.74
     was
    -0.57
     looking
    -0.55
    aktery
    -0.55
     is
    -0.55
     by
    -0.54
    ,
    -0.53
    一つ
    -0.51
     with
    -0.51
     recognising
    -0.50
    POSITIVE LOGITS
    ."));
    0.92
     greateſt
    0.88
     ſmall
    0.86
     ſeveral
    0.84
     faſt
    0.84
     myſelf
    0.82
     ſever
    0.81
     Diſ
    0.79
     Houſe
    0.79
     leaſt
    0.77
    Activations Density 1.166%

    No Known Activations