© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4140
    Prev
    Next
    INDEX
    Explanations

    XML or HTML-like tag endings and related attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OfYear
    -0.59
     Nunn
    -0.58
    ς
    -0.56
    ultar
    -0.56
    จำ
    -0.54
     Shum
    -0.53
     char
    -0.53
    mur
    -0.53
    ಷ
    -0.53
     shoe
    -0.53
    POSITIVE LOGITS
    "/>
    2.33
    "/>
    
    1.70
    }}/>
    1.66
    '/>
    1.64
    }/>
    1.54
    =""/>
    1.41
    />";
    1.36
    "/></
    1.36
    />
    1.27
    ]-->
    1.19
    Activations Density 0.009%

    No Known Activations