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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 3106
    Prev
    Next
    INDEX
    Explanations

    references to various countries and their interactions in political and historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.54
     فريبيس
    -0.53
    protoimpl
    -0.53
    Tikang
    -0.53
    tagHelperRunner
    -0.52
     terciopelo
    -0.52
    tosí
    -0.51
    ſcher
    -0.50
     Jérusalem
    -0.50
    adaptiveStyles
    -0.50
    POSITIVE LOGITS
     fVar
    0.39
     EU
    0.36
    EU
    0.35
     war
    0.32
     international
    0.31
     跳转至
    0.31
    cupertino
    0.30
     kal
    0.30
    complexType
    0.30
     wizy
    0.29
    Activations Density 0.776%

    No Known Activations