© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 5824
    Prev
    Next
    INDEX
    Explanations

    instances of structured data or encapsulated blocks of information, often indicated by special tokens or phrases

    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
    kháu
    -0.71
     corporativa
    -0.66
    tonode
    -0.63
    }*/
    -0.62
    }*/
    -0.61
     betweenstory
    -0.61
    يكب
    -0.60
    };*/
    -0.59
    fromnode
    -0.58
     InputDecoration
    -0.58
    POSITIVE LOGITS
     дописавши
    0.69
    geslacht
    0.61
    Datuak
    0.58
    abestanden
    0.57
     CommonModule
    0.56
    ResumeLayout
    0.56
    inį
    0.53
     lutter
    0.53
    erialization
    0.53
    💼
    0.51
    Activations Density 0.356%

    No Known Activations