© 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. 11-GEMMASCOPE-RES-16K
    11. 10456
    Prev
    Next
    INDEX
    Explanations

    references to folders and directory structures 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 @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    5
    -0.82
    cy
    -0.81
    c
    -0.78
    u
    -0.77
    ut
    -0.77
    2
    -0.76
    _{\
    -0.76
    o
    -0.76
    <b>
    -0.75
    mu
    -0.73
    POSITIVE LOGITS
     Anſ
    1.28
     themſelves
    1.27
     Theſe
    1.24
     Efq
    1.21
     doubtnut
    1.20
     itſelf
    1.18
     myſelf
    1.18
     $_"
    1.14
     Diſ
    1.12
     ―――――
    1.12
    Activations Density 0.198%

    No Known Activations