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. 16-GEMMASCOPE-RES-16K
    6. 12821
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and method calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets and hexadecimal values

    np_acts-logits-general · gemini-2.0-flash

    code and city names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessFile
    -0.55
     counter
    -0.50
     Pearce
    -0.49
     fit
    -0.48
    qai
    -0.47
    上角
    -0.46
     dagegen
    -0.45
    qü
    -0.44
    alat
    -0.42
     soft
    -0.42
    POSITIVE LOGITS
    CppMethod
    0.78
    AndEndTag
    0.75
     &___
    0.71
    /*
    0.69
     MonoBehaviour
    0.66
     CHICAGO
    0.65
    WAUKEE
    0.64
    ArgsConstructor
    0.64
     chicago
    0.64
     ioutil
    0.63
    Activations Density 0.027%

    No Known Activations