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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104614
    Prev
    Next
    INDEX
    Explanations

    verbs indicating possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     East
    -0.29
    super
    -0.28
    body
    -0.27
    East
    -0.27
     child
    -0.27
     Fre
    -0.27
    h
    -0.26
     blood
    -0.25
     darkness
    -0.25
    ca
    -0.25
    POSITIVE LOGITS
     queſto
    1.01
     ويكيپ
    0.94
    ſammen
    0.92
     FacebookSign
    0.89
     zwiſchen
    0.89
    CppMethod
    0.87
    ๣
    0.87
    <unused0>
    0.86
    ⏡
    0.85
    𨨏
    0.85
    Activations Density 0.036%

    No Known Activations