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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15712
    Prev
    Next
    INDEX
    Explanations

    negations and their variations related to beliefs and behaviors

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

    instances of the word "not" in contexts where it negates or contradicts an action, belief, or statement.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     nahilalakip
    -0.51
     насељу
    -0.51
     tartalomajánló
    -0.43
    .*")]
    -0.39
    oa̍t
    -0.39
     '\\;'
    -0.38
    ();?>
    -0.38
     Hohen
    -0.38
    PyExc
    -0.38
     Tief
    -0.37
    POSITIVE LOGITS
     cares
    0.67
     care
    0.63
     bothered
    0.59
    care
    0.55
     cared
    0.54
     caring
    0.53
    cares
    0.52
    exitRule
    0.52
    CARE
    0.50
     peduli
    0.50
    Activations Density 0.302%

    No Known Activations