© 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. 3-GEMMASCOPE-RES-16K
    11. 6687
    Prev
    Next
    INDEX
    Explanations

    adjectives and their variations that describe capabilities or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.42
    AndEndTag
    -0.39
    IsContent
    -0.36
     kuris
    -0.36
    Distribución
    -0.36
    Hentet
    -0.35
     distribution
    -0.35
    従
    -0.35
     Ab
    -0.34
     thank
    -0.34
    POSITIVE LOGITS
    able
    2.55
    ABLE
    1.88
    ables
    1.59
    ability
    1.53
    ably
    1.49
    ABLES
    1.27
    eable
    1.18
    ableness
    1.14
    ABILITY
    1.14
    ablemente
    1.10
    Activations Density 0.917%

    No Known Activations