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. 19-GEMMASCOPE-RES-16K
    6. 1996
    Prev
    Next
    INDEX
    Explanations

    terms related to mitochondrial function and particular types of cellular behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.67
    SerializedName
    -0.57
     AssemblyCompany
    -0.51
    SequentialGroup
    -0.50
    interopRequire
    -0.50
    truk
    -0.49
     tá
    -0.49
     quelle
    -0.47
     sala
    -0.47
    بات
    -0.46
    POSITIVE LOGITS
     Mith
    0.94
    Mith
    0.82
     Wikimedijinoj
    0.80
    Mí
    0.76
     Wolver
    0.71
    principalTable
    0.70
     Mih
    0.70
     NDEBUG
    0.69
     Mit
    0.67
     '*')
    0.66
    Activations Density 0.093%

    No Known Activations