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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 10361
    Prev
    Next
    INDEX
    Explanations

    references to physical barriers or walls and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.62
    invokeLater
    -0.61
     صوتيه
    -0.55
    RTGC
    -0.55
    formis
    -0.52
    EDEFAULT
    -0.50
    aibo
    -0.49
     INVENTION
    -0.49
    Atsauces
    -0.48
    Архівовано
    -0.48
    POSITIVE LOGITS
     wall
    3.18
     walls
    2.89
    wall
    2.68
     Wall
    2.63
    Wall
    2.56
     WALL
    2.53
    walls
    2.42
     Walls
    2.42
    WALL
    2.31
    Walls
    2.18
    Activations Density 0.335%

    No Known Activations