© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 766
    Prev
    Next
    INDEX
    Explanations

    code structures and elements related to object-relational mapping (ORM) in programming

    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
    bootstrapcdn
    -0.36
     Milk
    -0.35
     mil
    -0.35
     saites
    -0.33
     siga
    -0.33
     arch
    -0.32
     Ring
    -0.32
    NameValuePair
    -0.32
     sint
    -0.31
     rett
    -0.31
    POSITIVE LOGITS
     Symfony
    0.65
     decorazione
    0.63
    yntaxException
    0.62
     AppBundle
    0.61
    Symfony
    0.57
    IntoConstraints
    0.57
     coscienza
    0.55
     Doctrine
    0.54
    ########.
    0.54
     pérd
    0.51
    Activations Density 0.164%

    No Known Activations