© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 5140
    Prev
    Next
    INDEX
    Explanations

    references to organizations or groups, particularly in a sports or academic context

    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
     împre
    -0.66
     ragaz
    -0.66
     argint
    -0.64
     picioare
    -0.64
     uș
    -0.63
     piele
    -0.59
     maș
    -0.57
     îng
    -0.55
     săptăm
    -0.54
    toarele
    -0.53
    POSITIVE LOGITS
     Romanian
    0.71
     Bucharest
    0.65
    änien
    0.58
     Radu
    0.56
     Romania
    0.55
     kasarigan
    0.53
    Romania
    0.53
     Nicolae
    0.52
     Cluj
    0.50
    ResumeLayout
    0.49
    Activations Density 0.181%

    No Known Activations