© 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. 33-GEMMASCOPE-RES-16K
    6. 8442
    Prev
    Next
    INDEX
    Explanations

    personal experiences and expressions of emotion related to challenges and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بيها
    -0.36
    URLException
    -0.36
     ویکی‌پدیای
    -0.35
    Bibliograf
    -0.34
    InputBorder
    -0.32
    فيذ
    -0.32
     Ślą
    -0.32
    asteroide
    -0.32
    Dangerous
    -0.31
     naka
    -0.31
    POSITIVE LOGITS
     struggle
    2.55
     struggles
    2.48
     struggled
    2.44
     struggling
    2.38
     Struggle
    1.98
     strug
    1.95
    stru
    1.80
     kesulitan
    1.55
     difficulties
    1.48
     difficulty
    1.42
    Activations Density 0.504%

    No Known Activations