© 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. 40-GEMMASCOPE-RES-16K
    6. 2010
    Prev
    Next
    INDEX
    Explanations

    military and leadership roles in a historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.56
    IContainer
    -0.45
    tagHelperRunner
    -0.38
    calaureate
    -0.34
     vulner
    -0.34
    carteles
    -0.34
     crisis
    -0.34
     sakit
    -0.33
     inflex
    -0.33
     hosted
    -0.33
    POSITIVE LOGITS
     Ceylon
    0.58
     Constantinople
    0.56
     ब्रेकडाउन
    0.55
     Arabia
    0.54
     Jerusalem
    0.53
     Palestine
    0.49
     Hindustan
    0.49
     <<<<<<<<<<<<<<
    0.48
     Persia
    0.48
    Jerusalem
    0.48
    Activations Density 0.695%

    No Known Activations