© 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. 39-GEMMASCOPE-RES-16K
    6. 716
    Prev
    Next
    INDEX
    Explanations

    negative phrases and expressions of denial or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     puissent
    -0.82
     soient
    -0.80
     Be
    -0.72
    Be
    -0.70
    be
    -0.65
     aient
    -0.65
     siano
    -0.64
     fossero
    -0.58
     sejam
    -0.55
     be
    -0.54
    POSITIVE LOGITS
     belong
    1.23
     seem
    1.20
     deserve
    1.13
     exist
    1.06
     appear
    1.04
     need
    1.02
     owe
    0.98
     have
    0.97
     require
    0.94
     want
    0.90
    Activations Density 0.270%

    No Known Activations