© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5950
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the presence of various factors and their influences

    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
     noDo
    -0.65
     defaultstate
    -0.59
    StoryboardSegue
    -0.52
    msgTypes
    -0.52
    sidemargin
    -0.49
     msglen
    -0.47
     ***!
    -0.46
     typelib
    -0.46
    GEBURTSDATUM
    -0.46
     transfieras
    -0.45
    POSITIVE LOGITS
     factors
    3.34
     Factors
    2.91
    factors
    2.88
     factor
    2.84
    Factors
    2.77
     FACTORS
    2.61
     facteurs
    2.55
     faktor
    2.50
     factores
    2.48
    factor
    2.41
    Activations Density 1.053%

    No Known Activations