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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 4378
    Prev
    Next
    INDEX
    Explanations

    specific scientific or technical terms related to genetics and biochemistry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text after specific HTML heading tags

    np_acts-logits-general · gemini-2.0-flash

    acetylcholine receptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.99
    脚注の使い方
    -0.98
    Бахар
    -0.96
     الحره
    -0.95
     Bioaccumulative
    -0.92
     незавершена
    -0.89
    CloseOperation
    -0.89
    windowFixed
    -0.88
    IsMutable
    -0.88
    CppMethod
    -0.87
    POSITIVE LOGITS
    </h5>
    0.62
    </h2>
    0.59
    </h1>
    0.49
    </h3>
    0.46
    </h6>
    0.45
    </em>
    0.44
    </h4>
    0.42
     &
    0.42
     
    0.41
     podían
    0.40
    Activations Density 0.391%

    No Known Activations