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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15939
    Prev
    Next
    INDEX
    Explanations

    phrases related to belief and reliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.54
    SourceChecksum
    -0.53
    setArguments
    -0.51
    noopener
    -0.50
     BrowserModule
    -0.49
    StoryboardSegue
    -0.47
    ึ้น
    -0.47
     chẳng
    -0.46
    쁩
    -0.46
    おめでとうございます
    -0.45
    POSITIVE LOGITS
    躇
    0.55
     the
    0.54
     Administrativna
    0.47
     réparer
    0.45
     Manusia
    0.45
     múltiple
    0.45
     Confira
    0.44
     Estadual
    0.44
     táctil
    0.41
    rrggbb
    0.41
    Activations Density 0.414%

    No Known Activations