© 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. 5-GEMMASCOPE-RES-16K
    6. 8404
    Prev
    Next
    INDEX
    Explanations

    expressions of agreement or consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bul
    -0.75
    </em>
    -0.72
    Bul
    -0.65
    nP
    -0.65
     Dal
    -0.65
    mapsto
    -0.65
    dal
    -0.64
     Koz
    -0.64
    ாத
    -0.63
     Moran
    -0.63
    POSITIVE LOGITS
     Agree
    1.91
     Agreements
    1.87
     agrees
    1.87
     agree
    1.84
     Agreement
    1.80
     agreements
    1.80
     AGRE
    1.79
     agreement
    1.78
     agreed
    1.69
     Agre
    1.69
    Activations Density 0.079%

    No Known Activations