© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 15864
    Prev
    Next
    INDEX
    Explanations

    code-related elements and data handling structures in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngdoc
    -0.84
     Italijanski
    -0.72
    MessageTagHelper
    -0.71
    /**
    -0.69
    labelledby
    -0.64
     تانيه
    -0.63
     дописавши
    -0.59
    AndroidJUnit
    -0.59
    ="@+
    -0.58
    SBATCH
    -0.58
    POSITIVE LOGITS
     bytes
    1.16
    bytes
    1.03
     ByteArray
    0.94
    BYTES
    0.92
    GetBytes
    0.91
    Bytes
    0.89
     byte
    0.87
     Byte
    0.86
    getBytes
    0.85
    ByteArray
    0.85
    Activations Density 0.285%

    No Known Activations