© 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. 12753
    Prev
    Next
    INDEX
    Explanations

    terms related to poles and terminal points in a mathematical or physical context

    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
    iprot
    -0.46
    heça
    -0.42
    áctenos
    -0.41
    windowFixed
    -0.39
     myſelf
    -0.37
     Wicidata
    -0.37
     ProtoMessage
    -0.37
    بوابة
    -0.36
    adaptiveStyles
    -0.36
    shut
    -0.35
    POSITIVE LOGITS
     pole
    0.84
     Pole
    0.68
    Repository
    0.66
    Pole
    0.66
     terminal
    0.65
    pole
    0.64
    boil
    0.61
     terminals
    0.61
     boil
    0.60
    repo
    0.60
    Activations Density 0.552%

    No Known Activations