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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5890
    Prev
    Next
    INDEX
    Explanations

    titles and positions related to executive roles and senior leadership in organizations

    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
    MemoryWarning
    -0.47
     defaultstate
    -0.44
     příslu
    -0.41
    extAlignment
    -0.41
    böz
    -0.41
     OnInit
    -0.40
     BoxFit
    -0.40
    mobileqq
    -0.39
     diatas
    -0.39
    ROIT
    -0.39
    POSITIVE LOGITS
     assistant
    0.59
     Assistant
    0.57
     ASSISTANT
    0.56
     deputy
    0.56
    Assistant
    0.52
     Vice
    0.50
    assistant
    0.50
     assiste
    0.49
     vice
    0.49
     Deputy
    0.49
    Activations Density 0.276%

    No Known Activations