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. 40-GEMMASCOPE-RES-16K
    6. 5931
    Prev
    Next
    INDEX
    Explanations

    abbreviations, acronyms, and specific scientific terms related to medical and biological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ice
    -0.87
    ice
    -0.84
    Ice
    -0.82
     Ice
    -0.82
     يتيمه
    -0.81
     ICE
    -0.75
    MessageTagHelper
    -0.73
     تعدى
    -0.72
    ICE
    -0.71
     icy
    -0.69
    POSITIVE LOGITS
    )()
    0.52
    ]=>
    0.45
    )++;
    0.44
    ]**
    0.44
    }$​
    0.44
    )__
    0.43
    )`
    0.42
    ]&
    0.40
    }/*
    0.40
    )​
    0.39
    Activations Density 0.565%

    No Known Activations