© 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. 7837
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to variables and functions in a formal context

    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
    EndContext
    -0.46
    ctuation
    -0.45
    Nations
    -0.45
     paus
    -0.44
     wond
    -0.44
     itself
    -0.42
     Mende
    -0.42
    InfoList
    -0.42
    dersfield
    -0.42
     potes
    -0.42
    POSITIVE LOGITS
    ∀
    0.59
    forall
    0.55
    MigrationBuilder
    0.49
    Handlung
    0.46
    IsContent
    0.44
    VersionUID
    0.44
    
    0.44
     <<<<<<<<<<<<<<
    0.43
     tartalomajánló
    0.41
    ConstraintMaker
    0.41
    Activations Density 1.465%

    No Known Activations