© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8398
    Prev
    Next
    INDEX
    Explanations

    references to dogs and their interactions with humans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __(/*!
    -0.39
    jspx
    -0.35
    offsetHeight
    -0.35
    亨
    -0.33
     duch
    -0.33
    anteed
    -0.33
     demoral
    -0.32
     Selig
    -0.32
     श
    -0.32
    JAMIN
    -0.32
    POSITIVE LOGITS
     dogs
    1.28
     dog
    1.27
     canine
    1.20
     Dogs
    1.19
    Dogs
    1.17
    Dog
    1.10
    dogs
    1.09
    dog
    1.08
     mascotas
    1.06
     Canine
    1.06
    Activations Density 0.089%

    No Known Activations