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. 1-GEMMASCOPE-RES-16K
    6. 4284
    Prev
    Next
    INDEX
    Explanations

    expressions of hope

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ChromeDriver
    -0.70
    AndEndTag
    -0.67
    esModule
    -0.62
    apimachinery
    -0.60
     createSlice
    -0.59
     ());
    -0.59
     onAnimation
    -0.58
    richTextPanel
    -0.58
    colnshire
    -0.56
    <>());
    -0.56
    POSITIVE LOGITS
     Hope
    2.58
    Hope
    2.33
    HOPE
    1.69
     HOPE
    1.51
    hope
    1.20
     Hop
    0.84
    Glad
    0.81
     Faith
    0.78
     Grace
    0.76
    Hop
    0.75
    Activations Density 0.122%

    No Known Activations