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. 5-GEMMASCOPE-RES-16K
    6. 3546
    Prev
    Next
    INDEX
    Explanations

    references to fragments and their management in a programming context, particularly within a user interface framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -1.05
     dowry
    -0.99
     &___
    -0.97
     htons
    -0.94
    帖最后由
    -0.92
    NameInMap
    -0.91
    PostMapping
    -0.89
     mxArray
    -0.88
     "..\..\..\
    -0.87
     <>",
    -0.87
    POSITIVE LOGITS
    Fragment
    2.56
     Fragment
    2.45
     fragment
    2.42
    fragment
    2.31
     fragments
    2.09
    fragments
    1.97
     Fragments
    1.96
    Fragments
    1.82
    FRAGMENT
    1.78
     FRAG
    1.64
    Activations Density 0.068%

    No Known Activations