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. 18-GEMMASCOPE-RES-16K
    6. 3677
    Prev
    Next
    INDEX
    Explanations

    expressions of hope or optimism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "hope" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    Hope this helps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terase
    -0.67
    HtmlAttribute
    -0.59
    richTextPanel
    -0.57
     Dreyfus
    -0.57
     translateY
    -0.57
     protoimpl
    -0.56
    awtextra
    -0.54
    kubectl
    -0.53
     فہرست
    -0.53
    bage
    -0.52
    POSITIVE LOGITS
     HOPE
    1.30
     Hope
    1.28
    HOPE
    1.26
    hope
    1.25
     Hopes
    1.25
    Hope
    1.23
     hope
    1.22
     hopes
    1.22
     hoped
    1.00
     espoir
    0.98
    Activations Density 0.031%

    No Known Activations