© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 15226
    Prev
    Next
    INDEX
    Explanations

    references to spatial dimensions or axes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RUnlock
    -0.58
     BeautifulSoup
    -0.56
     INTERESAR
    -0.53
    הערות
    -0.52
     Grom
    -0.52
     comprom
    -0.50
    
    -0.49
     PopupWindow
    -0.49
    ữa
    -0.49
     gemeenten
    -0.48
    POSITIVE LOGITS
     axis
    4.50
    axis
    4.22
     Axis
    3.80
    Axis
    3.68
     AXIS
    3.17
    AXIS
    3.04
     axes
    3.02
     Axes
    2.39
    轴
    2.30
    軸
    2.15
    Activations Density 0.083%

    No Known Activations