© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 8911
    Prev
    Next
    INDEX
    Explanations

    phrases relating to challenges or difficulties in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     linkovi
    -0.62
    audiovisuel
    -0.61
     glau
    -0.59
    openConnection
    -0.58
     supers
    -0.58
     rem
    -0.56
     divin
    -0.56
    principalColumn
    -0.56
     IActionResult
    -0.55
     moul
    -0.55
    POSITIVE LOGITS
     difficulties
    1.44
     difficulté
    1.42
     difficult
    1.41
     dificultades
    1.39
     difficultés
    1.38
     dificuldades
    1.38
     difficulty
    1.33
     dificuldade
    1.29
     dificultad
    1.27
     difíciles
    1.25
    Activations Density 0.300%

    No Known Activations