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-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7309
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "g" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.53
    +#+#
    -0.51
     autorytatywna
    -0.49
    الحياه
    -0.48
    CppMethod
    -0.48
    óc
    -0.47
    υναι
    -0.46
    QMetaType
    -0.44
    InjectAttribute
    -0.43
    WireFormatLite
    -0.43
    POSITIVE LOGITS
    ao
    0.46
    upta
    0.45
    ail
    0.43
    ae
    0.38
    areth
    0.37
    aj
    0.36
     AppModule
    0.35
    hana
    0.35
    ordon
    0.34
    ary
    0.33
    Activations Density 0.184%

    No Known Activations