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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5163
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and their associated verbs or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.78
     дописавши
    -0.69
     Walkover
    -0.61
    Hentet
    -0.57
     صوتيه
    -0.56
     gyhoeddwyd
    -0.54
    يكب
    -0.52
    뀝
    -0.52
    })*/
    -0.52
    Autoritní
    -0.52
    POSITIVE LOGITS
    能够
    0.41
    比如说
    0.41
     solamente
    0.40
     سوف
    0.40
     concerning
    0.38
     existi
    0.38
    ciaż
    0.38
     entirety
    0.38
    Adapun
    0.38
     upon
    0.37
    Activations Density 0.354%

    No Known Activations