© 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. 8168
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "spring"

    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
    stateProvider
    -0.53
     Victoria
    -0.52
    DebuggerNonUser
    -0.51
     виправивши
    -0.49
     VICTORIA
    -0.48
    RTCF
    -0.48
     fran
    -0.47
     trait
    -0.47
     postIndex
    -0.46
     Assay
    -0.46
    POSITIVE LOGITS
     spring
    0.92
     summer
    0.92
    summer
    0.88
     verano
    0.80
     zomer
    0.79
    Spring
    0.77
    Summer
    0.74
     Spring
    0.71
     verão
    0.71
     Summer
    0.68
    Activations Density 0.147%

    No Known Activations