Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4632
    Prev
    Next
    INDEX
    Explanations

    the concept of difficulty and the use of the term "hard" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -1.21
    Datuak
    -1.16
     Rossetti
    -1.08
     propOrder
    -1.07
    :✨
    -1.06
    jsonwebtoken
    -1.04
    RegistryLite
    -1.01
     Walkover
    -0.99
    ollectionView
    -0.99
    yntaxException
    -0.99
    POSITIVE LOGITS
     HARD
    1.35
     hard
    1.30
     Hard
    1.28
    HARD
    1.26
    Hard
    1.22
    hard
    1.16
     Harding
    1.04
     Hardin
    0.97
    硬
    0.94
     hardness
    0.94
    Activations Density 0.072%

    No Known Activations