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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 29778
    Prev
    Next
    INDEX
    Explanations

    references to actions or states involving physical placement or positional relationships

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

    prepositional phrases involving nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     hagas
    -0.32
    不论
    -0.31
     vuonna
    -0.31
    Note
    -0.31
    無論
    -0.30
     ocasião
    -0.29
    This
    -0.29
     assistência
    -0.29
     ofrecemos
    -0.29
    The
    -0.28
    POSITIVE LOGITS
    \{\\
    0.68
    ſammen
    0.65
    нгред
    0.63
    oa̍t
    0.62
    oneofs
    0.62
    IUrlHelper
    0.61
     المعيارى
    0.60
    ðsíða
    0.58
    <unused8>
    0.57
    <unused74>
    0.57
    Activations Density 0.112%

    No Known Activations