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. 13-GEMMASCOPE-RES-16K
    6. 9983
    Prev
    Next
    INDEX
    Explanations

    repeated references to "the" and other determiners in the context of classification or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RetentionPolicy
    -0.93
     MaterialApp
    -0.86
     viewType
    -0.84
    IntoConstraints
    -0.81
     NSCoder
    -0.81
    djangoproject
    -0.80
    InvalidProtocol
    -0.80
    uxxxx
    -0.78
     doubtnut
    -0.76
    StoryboardSegue
    -0.76
    POSITIVE LOGITS
     following
    0.48
    ')";
    0.47
    ivat
    0.47
    <eos>
    0.47
    }}%
    0.46
     respective
    0.46
    %");
    0.45
     alapján
    0.43
    unit
    0.43
    numerusform
    0.43
    Activations Density 1.372%

    No Known Activations