Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15219
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and symbolic representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    ViewFeatures
    -0.59
    AndEndTag
    -0.59
    didSet
    -0.56
    setLayoutManager
    -0.55
    ngdoc
    -0.53
     ModelExpression
    -0.53
     autorytatywna
    -0.53
     transfieras
    -0.52
    cipar
    -0.51
    SOUNDBITE
    -0.50
    POSITIVE LOGITS
    发表于
    0.68
     emoticon
    0.60
     antemano
    0.57
     giggled
    0.57
    atação
    0.56
    ynx
    0.56
    ->__
    0.54
    脚注の使い方
    0.53
     muualla
    0.51
     manches
    0.51
    Activations Density 0.119%

    No Known Activations