© 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. 40-GEMMASCOPE-RES-16K
    6. 1472
    Prev
    Next
    INDEX
    Explanations

    components related to educational strategies and student support systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.72
    Erreferentziak
    -0.69
    rawDesc
    -0.61
     Superan
    -0.60
     enggak
    -0.59
     pinulongan
    -0.59
     otomatig
    -0.58
    WithIOException
    -0.57
    SPATH
    -0.57
     нем
    -0.57
    POSITIVE LOGITS
     RCMP
    1.37
     honoured
    1.35
    Colour
    1.34
     colour
    1.33
     Canadians
    1.30
     honour
    1.30
     labour
    1.30
     Canadian
    1.29
    labour
    1.28
     neighbourhoods
    1.28
    Activations Density 0.623%

    No Known Activations