© 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. 9-GEMMASCOPE-RES-16K
    11. 11272
    Prev
    Next
    INDEX
    Explanations

    references to technical or scientific methodologies

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

    phrases indicating limitations or constraints, particularly text that marks the end of a discussion or explanation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.45
    thâu
    -0.43
     Numerade
    -0.42
    什么呢
    -0.41
    MessageTagHelper
    -0.39
    来歴
    -0.36
    estacks
    -0.35
     sekali
    -0.35
     kolei
    -0.35
     eingel
    -0.35
    POSITIVE LOGITS
    脚注の使い方
    0.60
     esternos
    0.58
    ChildScrollView
    0.53
     كومونز
    0.50
    featureID
    0.49
    EndContext
    0.49
    ngdoc
    0.48
    AutoScale
    0.47
     تضيفلها
    0.46
     snippetHide
    0.46
    Activations Density 3.258%

    No Known Activations