© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8294
    Prev
    Next
    INDEX
    Explanations

    references to specific terms and measures in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.79
    eabouts
    -0.75
    /**
    -0.74
     Herrick
    -0.73
    /*
    -0.73
    starch
    -0.72
    )}}
    -0.71
     Newsroom
    -0.71
    findpost
    -0.70
     doInBackground
    -0.69
    POSITIVE LOGITS
    LE
    0.99
    le
    0.97
     Leona
    0.93
     Leandro
    0.91
     LE
    0.87
     Leighton
    0.85
     Leicestershire
    0.85
     Alejandro
    0.84
     Merle
    0.83
     BLE
    0.81
    Activations Density 0.348%

    No Known Activations