© 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. 23-GEMMASCOPE-RES-16K
    6. 9703
    Prev
    Next
    INDEX
    Explanations

    references to personal struggles and experiences related to self-expression on social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.63
    '],
    
    -0.48
    ɵɵelementStart
    -0.48
    "],
    
    -0.45
    FormTagHelper
    -0.45
    SharedCtor
    -0.45
    getMenuInflater
    -0.45
    IntegerField
    -0.43
    مراجع
    -0.42
    pim
    -0.42
    POSITIVE LOGITS
    хьтан
    0.56
     etc
    0.48
    Билгалдахарш
    0.46
    請繼續往下閱讀
    0.45
     blanches
    0.43
     kaarangay
    0.43
    性和
    0.42
     atque
    0.41
     그리고
    0.40
    DeleteBehavior
    0.40
    Activations Density 0.995%

    No Known Activations