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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24-GEMMASCOPE-RES-16K
    6. 14026
    Prev
    Next
    INDEX
    Explanations

    sections of code or commands in programming languages

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

    Code snippets and special characters

    np_acts-logits-general · gemini-2.0-flash

    code syntax elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omeness
    -0.64
    Enllaces
    -0.64
    ########.
    -0.61
    uxxxx
    -0.61
    posedge
    -0.60
     AssemblyProduct
    -0.59
     bezeichneter
    -0.57
     дописавши
    -0.57
    UnknownFields
    -0.57
     виправивши
    -0.56
    POSITIVE LOGITS
     //
    0.55
    //
    0.51
    //$
    0.50
     sintomi
    0.48
     ProtoMessage
    0.45
    //(
    0.44
    //"
    0.43
                
    0.43
     sintomas
    0.43
    getJob
    0.42
    Activations Density 0.031%

    No Known Activations