© 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. 0-GEMMASCOPE-RES-16K
    11. 1837
    Prev
    Next
    INDEX
    Explanations

    terms related to classification processes and procedures

    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
    on
    -0.60
     B
    -0.57
     
    -0.53
     K
    -0.52
     vzor
    -0.51
     IN
    -0.51
    вью
    -0.51
    a
    -0.49
     Ran
    -0.49
     Dan
    -0.49
    POSITIVE LOGITS
     Majefty
    1.48
    ſelf
    1.26
     Reſ
    1.23
     ſche
    1.23
     raiſ
    1.22
     myſelf
    1.20
     Houſe
    1.19
     Monfieur
    1.17
     Anſ
    1.15
     pleaſure
    1.14
    Activations Density 0.069%

    No Known Activations