Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 195
    Prev
    Next
    INDEX
    Explanations

    punctuation and parentheses used in various contexts

    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
    richTextPanel
    -0.58
     ProtoMessage
    -0.49
    ConstraintMaker
    -0.48
    GEBURTS
    -0.46
     Audiodateien
    -0.45
    ---*/
    -0.44
     unknownFields
    -0.43
     vPvB
    -0.42
    prepareStatement
    -0.42
    AddTagHelper
    -0.42
    POSITIVE LOGITS
     The
    0.70
    The
    0.68
    
    0.57
    There
    0.56
     There
    0.55
    They
    0.54
     disambiguazione
    0.52
     Memiliki
    0.51
     Grecs
    0.50
     faptul
    0.50
    Activations Density 0.523%

    No Known Activations