© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 4519
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and underscores in code-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.59
     noDo
    -0.57
    StoryboardSegue
    -0.56
     ſta
    -0.56
     linkovi
    -0.55
    ſelves
    -0.53
     decimal
    -0.53
    PhysRevD
    -0.52
     Rigidbody
    -0.52
    sidemargin
    -0.50
    POSITIVE LOGITS
     trekken
    0.54
     ilgili
    0.47
    ıdır
    0.46
    l
    0.45
     ExecuteAsync
    0.44
    led
    0.43
     beraber
    0.42
     birlikte
    0.42
    liai
    0.41
    el
    0.41
    Activations Density 0.833%

    No Known Activations