Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2643
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pass" and related variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.44
    DECREF
    -0.43
    كويكب
    -0.42
    Vidite
    -0.42
     kasarigan
    -0.42
     vainqueur
    -0.41
    antaranya
    -0.37
    ximately
    -0.37
     Seigneur
    -0.36
    InitVars
    -0.36
    POSITIVE LOGITS
     Pass
    3.06
    Pass
    2.94
    pass
    2.92
     PASS
    2.83
     pass
    2.78
     Pas
    2.72
    PASS
    2.67
    Pas
    2.66
     pas
    2.61
    pas
    2.39
    Activations Density 0.152%

    No Known Activations