© 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. 6745
    Prev
    Next
    INDEX
    Explanations

    terms related to evaluation and assessment processes

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

    the word "evaluation" appearing in academic and technical documents.

    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
    onAttach
    -0.51
     poffible
    -0.50
    قایناقلار
    -0.46
    twimg
    -0.46
    tableFuture
    -0.45
     PublicKey
    -0.45
     étrangère
    -0.45
     étrangères
    -0.45
     TMPro
    -0.44
    gdx
    -0.44
    POSITIVE LOGITS
     EVALU
    0.55
    EVALU
    0.53
     evaluates
    0.50
     avaliação
    0.49
     Evalu
    0.49
     avaliar
    0.48
     evaluating
    0.47
     evaluate
    0.46
    Evalu
    0.46
     Evaluating
    0.46
    Activations Density 0.358%

    No Known Activations