© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 72015
    Prev
    Next
    INDEX
    Explanations

    assertions and recommendations regarding the necessity or probability of actions or conditions

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

    states what is necessary or possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     however
    -0.94
    however
    -0.81
     meanwhile
    -0.81
     però
    -0.78
     cependant
    -0.71
     toutefois
    -0.69
     azonban
    -0.68
    However
    -0.66
     entanto
    -0.65
     ugy
    -0.65
    POSITIVE LOGITS
    必然
    0.68
     becomes
    0.65
     inevitably
    0.60
     indirec
    0.60
     naturally
    0.60
    จึง
    0.59
     necessarily
    0.59
     indirectly
    0.59
    becomes
    0.56
     doubly
    0.55
    Activations Density 0.311%

    No Known Activations