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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6813
    Prev
    Next
    INDEX
    Explanations

    the word "while", and to a lesser extent, "if" and "is".

    oai_token-act-pair · gemini-2.0-flash

    while

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.60
    ChildScrollView
    -0.58
    setVerticalGroup
    -0.58
    IContainer
    -0.55
    <bos>
    -0.55
    })));
    -0.54
    protoimpl
    -0.54
     Roskov
    -0.53
    }));
    
    -0.52
     although
    -0.49
    POSITIVE LOGITS
    writeField
    0.65
    uspiel
    0.56
    ispiele
    0.54
     Kase
    0.52
     touristes
    0.51
     thèmes
    0.51
    setViewportView
    0.51
    Havolalar
    0.50
    emus
    0.50
    ình
    0.49
    Activations Density 1.817%

    No Known Activations