Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12800
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking help or guidance regarding financial or personal assistance

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

    Follows prepositions "with", "by", "for"

    np_acts-logits-general · gemini-2.0-flash

    PIP and deprivation

    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
    cticut
    -0.65
    uland
    -0.59
     समीक्षाओं
    -0.59
    évaluateur
    -0.58
    Искәрмәләр
    -0.57
     상세
    -0.57
     esternos
    -0.56
    SpringRunner
    -0.56
    存于互联网档案馆
    -0.55
     Dames
    -0.54
    POSITIVE LOGITS
     rough
    0.62
     looked
    0.60
     Looked
    0.59
    Bioaccumulative
    0.58
    looked
    0.57
     lone
    0.56
     Traveller
    0.56
     SEND
    0.54
     vulnerable
    0.54
    rungsseite
    0.54
    Activations Density 0.222%

    No Known Activations