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. 24-GEMMASCOPE-RES-16K
    6. 2504
    Prev
    Next
    INDEX
    Explanations

    phrases that express comparisons and assessments of worth or capability

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

    Personal pronouns followed by a verb "to be"

    np_acts-logits-general · gemini-2.0-flash

    I am she is they are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.70
    UnusedPrivate
    -0.68
     ostavi
    -0.61
    doesn
    -0.58
     Doesn
    -0.57
    DockStyle
    -0.57
     consultato
    -0.56
    Doesn
    -0.56
     مشين
    -0.55
     ندارد
    -0.54
    POSITIVE LOGITS
    Хьажоргаш
    0.51
     lehe
    0.51
     isto
    0.49
     manifestly
    0.47
     paraître
    0.43
     byť
    0.42
    apnews
    0.42
    designation
    0.42
    竟然是
    0.42
     яви
    0.42
    Activations Density 0.103%

    No Known Activations