© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9343
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or terms related to "dia" and "neck."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.51
     Demographics
    -0.47
    ellschaft
    -0.44
    vener
    -0.42
    mauer
    -0.42
    الحياه
    -0.41
    openSession
    -0.41
    BagLayout
    -0.40
    پیوند
    -0.39
    Pyx
    -0.39
    POSITIVE LOGITS
     Signalez
    0.89
     Certified
    0.69
     Nar
    0.67
    Certified
    0.66
     nar
    0.66
    certified
    0.65
     certified
    0.63
     GenerationType
    0.62
    Nar
    0.59
    يكب
    0.55
    Activations Density 0.149%

    No Known Activations