© 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. 587
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations and entities

    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
    Besides
    -0.43
     Besides
    -0.40
    GEBURTSDATUM
    -0.40
     propOrder
    -0.38
     Biaya
    -0.38
     econô
    -0.36
     suaves
    -0.36
     căr
    -0.36
     Jenderal
    -0.36
    тьяна
    -0.35
    POSITIVE LOGITS
    dersfield
    0.54
    migrationBuilder
    0.54
     endblock
    0.54
     postcode
    0.53
    thorpe
    0.52
     (£
    0.51
     rhestr
    0.51
     tyres
    0.48
    AddTagHelper
    0.48
    的问道
    0.47
    Activations Density 0.285%

    No Known Activations