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. 36-GEMMASCOPE-RES-16K
    6. 11684
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vPvB
    -0.51
     لينك
    -0.49
    abetes
    -0.48
    itteet
    -0.47
    kenes
    -0.46
    ocrats
    -0.45
    hies
    -0.42
    inoj
    -0.42
    heon
    -0.42
    Географи
    -0.42
    POSITIVE LOGITS
    ’
    0.93
    Дереккөздер
    0.57
    WireFormatLite
    0.53
    fjspx
    0.52
     étoient
    0.46
    '
    0.46
    原始内容存档于
    0.44
    了口气
    0.41
    SuspendLayout
    0.41
    PostMapping
    0.39
    Activations Density 0.731%

    No Known Activations