© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 14591
    Prev
    Next
    INDEX
    Explanations

    expressions and sentiments associated with motherhood and personal pride

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

    the neuron detects words and phrases that mark strong evaluation, preference, or superlative emphasis in a sentence.

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cherchés
    -0.50
     يتيمه
    -0.47
    WireFormat
    -0.47
    tagHelper
    -0.43
    Personendaten
    -0.43
     InputDecoration
    -0.42
     ProtoMessage
    -0.42
    alai
    -0.42
    GraphicsUnit
    -0.42
     grado
    -0.41
    POSITIVE LOGITS
    </>
    0.68
    }{*}{
    0.65
     contd
    0.63
    คือ
    0.62
    awakeFromNib
    0.60
    TagHelper
    0.59
     ddelweddau
    0.59
     useState
    0.58
    Depends
    0.56
     LXXX
    0.55
    Activations Density 0.269%

    No Known Activations