© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 8997
    Prev
    Next
    INDEX
    Explanations

    terms associated with changes in state or conditions, particularly in a scientific or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.59
    MessageTagHelper
    -0.57
     Мексичка
    -0.55
     препратки
    -0.54
    -------
    -0.52
    éndole
    -0.50
    ↹
    -0.48
     Wiktionnaire
    -0.47
    jgl
    -0.46
    posables
    -0.46
    POSITIVE LOGITS
    clearInterval
    0.41
     händer
    0.40
    ngrx
    0.39
    MockBean
    0.38
    printStackTrace
    0.37
    IGraphics
    0.36
    AndUpdate
    0.36
     stringBy
    0.35
     Geografia
    0.34
     voce
    0.34
    Activations Density 1.395%

    No Known Activations