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. 21-GEMMASCOPE-RES-16K
    6. 15329
    Prev
    Next
    INDEX
    Explanations

    discussions about consequences and implications of actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oneofs
    -0.54
     informée
    -0.52
    ChildScrollView
    -0.51
     الرياضيه
    -0.49
    piración
    -0.47
     Spisak
    -0.47
    errHandler
    -0.46
     stuks
    -0.45
    曖昧さ回避
    -0.44
    écnicas
    -0.43
    POSITIVE LOGITS
     consequences
    1.22
    Consequences
    1.05
     Consequences
    1.00
     conséquences
    1.00
     impact
    0.98
     effects
    0.97
     effect
    0.96
     repercussions
    0.91
     impacts
    0.91
     consequence
    0.90
    Activations Density 0.556%

    No Known Activations