© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 716
    Prev
    Next
    INDEX
    Explanations

    phrases related to combinations of therapies and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    combination therapies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.50
    assurer
    -0.49
    versal
    -0.47
    vacy
    -0.45
    lapsible
    -0.44
     ddelweddau
    -0.44
    丈
    -0.44
     Isolated
    -0.42
     Disconnect
    -0.42
    contentLoaded
    -0.42
    POSITIVE LOGITS
     combinations
    0.67
     together
    0.63
     совмест
    0.60
     joint
    0.57
     Together
    0.57
    Together
    0.56
     együtt
    0.55
     jointly
    0.53
     partners
    0.52
     combination
    0.52
    Activations Density 0.201%

    No Known Activations