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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53271
    Prev
    Next
    INDEX
    Explanations

    conditional statements and checks for the presence of variables in code

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

    code, programming, and language

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ;
    -0.48
     Vries
    -0.46
    ();
    -0.46
     to
    -0.45
     being
    -0.43
     se
    -0.42
     mắn
    -0.42
    .;
    -0.39
    1
    -0.39
    };
    -0.39
    POSITIVE LOGITS
     صوتيه
    0.97
     يتيمه
    0.91
     فريبيس
    0.86
    GEBURTSDATUM
    0.83
    enumi
    0.81
     Autorisations
    0.80
     _$
    0.79
     ſmall
    0.78
    MemoryWarning
    0.76
    IUrlHelper
    0.76
    Activations Density 0.009%

    No Known Activations