© 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. 31-GEMMASCOPE-RES-16K
    11. 12753
    Prev
    Next
    INDEX
    Explanations

    administrative and evaluative nuances in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    negative conditional statements using "if not" constructions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.45
    SBATCH
    -0.45
    WebMethod
    -0.44
     ContentValues
    -0.42
     bezeichneter
    -0.40
    reportWebVitals
    -0.40
    nodoc
    -0.40
    verwijspagina
    -0.38
     imperfect
    -0.37
    Попис
    -0.36
    POSITIVE LOGITS
     outright
    2.11
     downright
    1.88
     directamente
    1.08
     carré
    1.07
     přímo
    1.06
     straight
    1.05
     altogether
    0.98
     blatantly
    0.94
     flatly
    0.93
     directly
    0.91
    Activations Density 0.449%

    No Known Activations