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. 20-GEMMASCOPE-RES-16K
    6. 16215
    Prev
    Next
    INDEX
    Explanations

    phrases describing experiences and feelings related to personal and professional life

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

    preceding or related to appearance

    np_acts-logits-general · gemini-2.0-flash

    what something looks like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chi̍t
    -0.57
    VolleyError
    -0.55
     circo
    -0.53
    HasForeignKey
    -0.52
    Portail
    -0.51
    лару
    -0.51
     bakar
    -0.51
    égard
    -0.50
     betweenstory
    -0.49
     actionMode
    -0.49
    POSITIVE LOGITS
     like
    0.89
     look
    0.75
     looks
    0.74
     looked
    0.71
     LIKE
    0.67
     ressemb
    0.66
     trông
    0.65
     Looks
    0.65
     feel
    0.64
     ressemble
    0.64
    Activations Density 0.102%

    No Known Activations