Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 8219
    Prev
    Next
    INDEX
    Explanations

    phrases related to gradual progression and incremental changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugc
    -0.56
    ukat
    -0.53
    vale
    -0.50
     CURIAM
    -0.49
     وتسجيلات
    -0.48
    glBindTexture
    -0.47
    StoreMessageInfo
    -0.47
     мет
    -0.46
    рс
    -0.46
    ValueOf
    -0.45
    POSITIVE LOGITS
    Slowly
    0.94
     gradual
    0.94
     Slowly
    0.93
     slowly
    0.86
    AutoScaleMode
    0.86
     Gradually
    0.86
    slowly
    0.84
     incremental
    0.81
    tagHelperRunner
    0.79
     lentamente
    0.78
    Activations Density 0.337%

    No Known Activations