© 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. 23-GEMMASCOPE-RES-16K
    6. 8996
    Prev
    Next
    INDEX
    Explanations

    references to gameplay mechanics and healthcare-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المناصب
    -0.49
    Notae
    -0.48
    thenReturn
    -0.48
    bufio
    -0.48
    curator
    -0.48
     Russians
    -0.47
    /*
    -0.47
    Спасылкі
    -0.46
    ellido
    -0.46
    routeProvider
    -0.46
    POSITIVE LOGITS
    shadowOffset
    0.51
     lifetime
    0.50
    kā
    0.50
     ecos
    0.49
    Życiorys
    0.47
     comprom
    0.47
    Lifetime
    0.47
    phazard
    0.47
    󠁢
    0.47
    Heartbeat
    0.46
    Activations Density 1.124%

    No Known Activations