© 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 - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 9853
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'hard' and its variations, indicating a focus on effort or difficulty

    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
     consentement
    -0.61
     Rossetti
    -0.57
    seamnă
    -0.56
     Drapeau
    -0.53
    ῷ
    -0.53
     يتيمه
    -0.53
    aneity
    -0.53
     Phipps
    -0.52
    toplankton
    -0.52
    urora
    -0.52
    POSITIVE LOGITS
     hard
    4.79
    hard
    4.32
     Hard
    4.24
    Hard
    4.23
     HARD
    3.89
    HARD
    3.84
     harder
    3.33
     hardest
    3.05
     harde
    2.79
     Harder
    2.60
    Activations Density 0.044%

    No Known Activations