© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11171
    Prev
    Next
    INDEX
    Explanations

    programming syntax, specifically related to the structure of string declarations and greetings in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.31
    يكب
    -0.31
    加坡
    -0.30
    NameInMap
    -0.28
    ParseTree
    -0.27
    RTLR
    -0.27
    xnn
    -0.26
     đích
    -0.26
    rophoresis
    -0.26
     quia
    -0.26
    POSITIVE LOGITS
     hello
    2.63
     Hello
    2.56
    Hello
    2.27
     greetings
    2.22
     greeting
    2.17
     Greetings
    2.17
    hello
    2.08
     HELLO
    2.03
    Greetings
    2.03
    HELLO
    1.86
    Activations Density 0.403%

    No Known Activations