© 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. 7-GEMMASCOPE-RES-16K
    11. 15756
    Prev
    Next
    INDEX
    Explanations

    data types and properties related to scientific measurements or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -1.02
     незавершена
    -1.00
    AndEndTag
    -0.99
     كومونز
    -0.90
    tagHelperRunner
    -0.85
    ScopeManager
    -0.84
     дописавши
    -0.83
     CreateTagHelper
    -0.82
     Италијани
    -0.82
    ⓧ
    -0.79
    POSITIVE LOGITS
    </h2>
    0.71
    </h1>
    0.52
    </strong>
    0.50
    ↵
    0.45
     مختلفة
    0.45
    </em>
    0.44
    0.43
    </h3>
    0.42
    </h5>
    0.41
    _
    0.40
    Activations Density 0.143%
    No Known Activations