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. 23-GEMMASCOPE-RES-16K
    6. 7604
    Prev
    Next
    INDEX
    Explanations

    references to individuals' artistic capabilities and careers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.60
    atguigu
    -0.59
    internalType
    -0.58
     hearers
    -0.52
     MainAxisSize
    -0.49
     député
    -0.48
    GIVEREF
    -0.48
     doInBackground
    -0.47
    RegistryLite
    -0.47
     démission
    -0.47
    POSITIVE LOGITS
     photography
    1.97
     photographing
    1.93
     photographer
    1.91
     photographers
    1.91
     photo
    1.81
     photograph
    1.79
    Photograph
    1.75
     Photography
    1.74
     photographed
    1.72
     photographic
    1.69
    Activations Density 0.319%

    No Known Activations