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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12285
    Prev
    Next
    INDEX
    Explanations

    academic qualifications and educational credentials

    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
     المعيارى
    -0.68
     himo
    -0.63
     <=",
    -0.58
     cref
    -0.56
    alties
    -0.54
     يتيمه
    -0.48
     للمعارف
    -0.48
    ativement
    -0.48
    gonic
    -0.47
    </tfoot>
    -0.47
    POSITIVE LOGITS
     master
    1.69
     Master
    1.66
     masters
    1.66
     Masters
    1.62
    Master
    1.47
    Masters
    1.45
    masters
    1.44
     PhD
    1.39
     MASTER
    1.38
     doctorate
    1.38
    Activations Density 0.187%

    No Known Activations