© 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. 31-GEMMASCOPE-RES-16K
    6. 2773
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating actions or processes

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

    past tense verbs in the form "was [past participle]" or "was [verb]".

    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
     resourceCulture
    -0.50
    قایناقلار
    -0.48
    ResumeLayout
    -0.47
     autorytatywna
    -0.44
    NameInMap
    -0.41
    TemporalType
    -0.40
    良かった
    -0.39
    TextBoxColumn
    -0.38
    ByVersion
    -0.38
     now
    -0.37
    POSITIVE LOGITS
     formerly
    0.81
     previously
    0.79
     recently
    0.77
    previously
    0.73
    recently
    0.72
     vroeger
    0.72
     recentemente
    0.70
    formerly
    0.68
     autrefois
    0.68
     Previously
    0.67
    Activations Density 0.406%

    No Known Activations