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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6845
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and function calls in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    " +=" in code or text

    np_acts-logits-general · gemini-2.0-flash

    += followed by assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chriftian
    -0.53
    ulemon
    -0.50
    Vidite
    -0.50
    Personendaten
    -0.48
    Bibliograf
    -0.47
    存于互联网档案馆
    -0.47
     houſe
    -0.47
    felves
    -0.47
    ArgumentParser
    -0.45
     onely
    -0.45
    POSITIVE LOGITS
     +=
    2.03
    +=
    1.51
     -=
    1.49
    ]+=
    1.38
     *=
    1.26
    +=(
    1.14
     .=
    1.08
     /=
    0.99
    +="
    0.99
     |=
    0.97
    Activations Density 0.126%

    No Known Activations