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. 4-GEMMASCOPE-RES-16K
    6. 10710
    Prev
    Next
    INDEX
    Explanations

    usage of the word "with" 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 @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerNonUser
    -1.05
     JpaRepository
    -0.86
     Normdatei
    -0.77
    MemoryWarning
    -0.75
     يتيمه
    -0.74
    存于互联网档案馆
    -0.74
    Hentet
    -0.73
    RenderAtEndOf
    -0.72
    GraphicsUnit
    -0.71
    modelBuilder
    -0.71
    POSITIVE LOGITS
    搭配
    0.59
     paired
    0.54
     Pairing
    0.53
     pairing
    0.49
    bonus
    0.49
     pairs
    0.47
     搭配
    0.47
    Pairing
    0.45
     STACK
    0.45
     dazu
    0.45
    Activations Density 0.517%

    No Known Activations