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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4434
    Prev
    Next
    INDEX
    Explanations

    terms and references related to web technologies and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleType
    -0.49
    CppMethod
    -0.46
    BASEPATH
    -0.43
     betweenstory
    -0.42
    WithIOException
    -0.41
    afficheront
    -0.41
    BagLayout
    -0.38
    __((
    -0.37
     proprement
    -0.37
     jendela
    -0.36
    POSITIVE LOGITS
    httphttps
    0.51
    qtype
    0.46
    GEBURTS
    0.44
    岗
    0.43
    الدراسه
    0.43
     EconPapers
    0.43
    лтемелер
    0.40
     Ums
    0.40
    irvana
    0.40
     QM
    0.40
    Activations Density 0.592%

    No Known Activations