© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 56539
    Prev
    Next
    INDEX
    Explanations

    phrases related to restructuring or separating organizations, particularly in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    haustible
    -0.54
    fır
    -0.52
     бор
    -0.48
    Rede
    -0.47
    émoc
    -0.47
    emplar
    -0.46
     Laramie
    -0.45
    ☾
    -0.45
    примеча
    -0.44
     követ
    -0.44
    POSITIVE LOGITS
     splits
    1.15
     splitting
    1.14
     split
    1.13
     Split
    1.07
     breakup
    1.06
    Split
    1.05
    split
    1.00
     fragmentation
    0.98
     separating
    0.98
    splitting
    0.97
    Activations Density 0.123%

    No Known Activations