© 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-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 10264
    Prev
    Next
    INDEX
    Explanations

    block comments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
     Defensa
    -0.46
    SpringRunner
    -0.45
    "},
    
    -0.44
     autoridad
    -0.43
     Administrativna
    -0.42
     doctrina
    -0.41
    ")));
    
    -0.41
    setField
    -0.41
    lámpara
    -0.41
    their
    -0.41
    POSITIVE LOGITS
    /*
    2.03
    /*
    1.94
     /*
    1.81
    (/*
    1.38
    }/*
    1.34
    +/*
    1.28
    /*
    
    1.19
    /*!
    1.14
    /*"
    1.13
    /*@
    1.10
    Activations Density 0.206%

    No Known Activations