© 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. 2-GEMMASCOPE-RES-16K
    6. 3991
    Prev
    Next
    INDEX
    Explanations

    references to leadership or authoritative positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OFDb
    -0.51
    angliski
    -0.47
    Rüyada
    -0.46
    ellees
    -0.45
    ValueStyle
    -0.45
    azaki
    -0.41
    msgTypes
    -0.39
    ünste
    -0.39
    原始内容存档
    -0.39
    Tikang
    -0.39
    POSITIVE LOGITS
     head
    4.03
     Head
    3.97
    Head
    3.78
     HEAD
    3.44
    head
    3.38
    HEAD
    3.06
     heads
    3.05
     Heads
    2.83
    heads
    2.59
    ヘッド
    2.53
    Activations Density 0.116%

    No Known Activations