© 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. 6-GEMMASCOPE-RES-16K
    6. 2217
    Prev
    Next
    INDEX
    Explanations

    blockquote elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Koc
    -0.71
    ষ্
    -0.65
     mit
    -0.63
     Hirst
    -0.63
     nang
    -0.60
    lblNewLabel
    -0.58
     gali
    -0.56
     Walsh
    -0.56
    PropertyChanged
    -0.56
    önt
    -0.56
    POSITIVE LOGITS
    </blockquote>
    2.50
    \]
    1.48
    }\]
    1.34
    )";
    1.24
    findpost
    1.23
    )";
    
    1.22
    ).”
    1.21
    ’.”
    1.16
    .";
    1.15
    >`;
    1.15
    Activations Density 0.076%

    No Known Activations