© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8862
    Prev
    Next
    INDEX
    Explanations

    references to the term "ASS" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     nonUne
    -0.48
     Administrativna
    -0.47
    empêcher
    -0.47
    épreuve
    -0.46
    équipement
    -0.43
    hygiène
    -0.43
    LookAnd
    -0.42
    Története
    -0.42
    extérieur
    -0.42
    étranger
    -0.42
    POSITIVE LOGITS
     ASS
    1.88
     Ass
    1.85
     Asp
    1.82
     ASH
    1.82
     Ash
    1.80
    ASS
    1.79
    Ass
    1.77
     ass
    1.77
    Asp
    1.77
     ASC
    1.76
    Activations Density 0.774%

    No Known Activations