© 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. 6815
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly in the context of time and significant years

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

    four-digit years, particularly in the format of "20XX".

    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
     Constitutional
    -0.46
     antim
    -0.44
     betweenstory
    -0.44
    PMailer
    -0.44
     Constitution
    -0.43
     Extraction
    -0.42
     Pandemic
    -0.42
    itrine
    -0.42
     Clam
    -0.42
     Meth
    -0.41
    POSITIVE LOGITS
    Personendaten
    0.54
    tangentMode
    0.51
     Audiodateien
    0.46
     ocasião
    0.42
     econômica
    0.42
     simplicité
    0.40
     suivante
    0.39
     Umgebung
    0.39
     comodidad
    0.39
    SuccessListener
    0.39
    Activations Density 0.392%

    No Known Activations