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
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 144
    Prev
    Next
    INDEX
    Explanations

    fragments that include specific personal identifiers or metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hoeddwyd
    -0.58
    LEGGI
    -0.57
     føl
    -0.56
     HasFactory
    -0.56
    verwijspagina
    -0.54
    Personensuche
    -0.53
    OCCURRED
    -0.51
    ViewInit
    -0.50
     esternos
    -0.50
    envolvimento
    -0.49
    POSITIVE LOGITS
    店で
    0.41
     thus
    0.37
     Yorkers
    0.37
    ByEmail
    0.36
     Thus
    0.36
    ियों
    0.36
    Thus
    0.35
    dataIndex
    0.35
    AndPassword
    0.35
    ickness
    0.34
    Activations Density 0.119%

    No Known Activations