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. 3-GEMMASCOPE-RES-16K
    6. 12873
    Prev
    Next
    INDEX
    Explanations

    the concept of authenticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.88
    endpush
    -0.75
    Calais
    -0.74
     فريبيس
    -0.72
    gdx
    -0.71
    yargs
    -0.70
    mapreduce
    -0.69
     Markle
    -0.68
    yaar
    -0.68
     PeEnEo
    -0.67
    POSITIVE LOGITS
     authentic
    2.57
    Authentic
    2.40
     Authentic
    2.33
    authentic
    2.30
     authenticity
    2.19
     Authenticity
    1.93
     authentique
    1.84
     autenti
    1.71
     authenti
    1.60
     autentic
    1.58
    Activations Density 0.082%

    No Known Activations