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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 6417
    Prev
    Next
    INDEX
    Explanations

    sentences relating to mythical characters or entities

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

    Followed by non-English words/characters

    np_acts-logits-general · gemini-2.0-flash

    kalo tak, tetapi, だけど

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NUMX
    -0.65
    UnsafeEnabled
    -0.60
    __":
    -0.58
    这让
    -0.58
     ?',
    -0.57
    ])):
    -0.56
    Obrigada
    -0.56
    NOPQRST
    -0.56
     XNUMX
    -0.56
    pportun
    -0.55
    POSITIVE LOGITS
    Portály
    0.67
     already
    0.63
     still
    0.63
     not
    0.60
     sometimes
    0.58
    tagHelper
    0.57
     Already
    0.57
     Afraid
    0.53
    叫
    0.53
     مفص
    0.52
    Activations Density 0.122%

    No Known Activations