© 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. 8-GEMMASCOPE-RES-16K
    6. 3498
    Prev
    Next
    INDEX
    Explanations

    terms related to optical alignment processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.87
    WebMethod
    -0.86
    حياته
    -0.83
    expandindo
    -0.77
    ⓧ
    -0.76
     Cutler
    -0.74
    Vase
    -0.74
    sidemargin
    -0.73
    ductory
    -0.71
    marvin
    -0.71
    POSITIVE LOGITS
    }}/>
    0.80
     Alignment
    0.76
     Yee
    0.75
     Allianz
    0.75
     Alli
    0.73
    Alliance
    0.70
     alignment
    0.70
     compliant
    0.69
     aligns
    0.68
     alignments
    0.68
    Activations Density 0.191%

    No Known Activations