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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 6623
    Prev
    Next
    INDEX
    Explanations

    topics related to geopolitical tensions and military actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
     виправивши
    -0.50
    balleur
    -0.50
     تضيفلها
    -0.49
    .*")]
    -0.46
    WithIOException
    -0.46
     snippetHide
    -0.46
     సౌకర్య
    -0.45
    HostException
    -0.43
     Lokales
    -0.42
     trainer
    -0.42
    POSITIVE LOGITS
    AssignableFrom
    0.42
     zwaar
    0.42
     political
    0.40
     politically
    0.40
     çıkar
    0.39
     weakened
    0.39
    apnews
    0.38
     threatened
    0.38
     declared
    0.38
     threatens
    0.37
    Activations Density 0.898%

    No Known Activations