© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9146
    Prev
    Next
    INDEX
    Explanations

    verbs related to encouragement or support

    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
    mybatisplus
    -0.83
     cref
    -0.65
    opheles
    -0.57
     numberOfRows
    -0.56
    이션
    -0.55
    aurus
    -0.55
    strophe
    -0.54
    Datagram
    -0.53
    principalColumn
    -0.53
     linkovi
    -0.53
    POSITIVE LOGITS
     encourage
    1.75
     promote
    1.70
     stimulate
    1.66
     promoting
    1.63
     Promote
    1.59
     Encourage
    1.58
     promotes
    1.54
    Promote
    1.53
     stimulates
    1.52
     encourages
    1.51
    Activations Density 0.115%

    No Known Activations