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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3867
    Prev
    Next
    INDEX
    Explanations

    references to the word "tail" and its variations

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

    "tail" or "tailed"

    np_acts-logits-general · gemini-2.0-flash

    literal tail appendage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bibliograf
    -0.47
    Autoritní
    -0.47
     Bloc
    -0.44
     TPS
    -0.44
    HasAnnotation
    -0.44
    googleapis
    -0.42
    bloc
    -0.42
    TPS
    -0.40
     TPU
    -0.40
    TSP
    -0.40
    POSITIVE LOGITS
     tail
    2.52
    tail
    2.31
     Tail
    2.28
    Tail
    2.25
     tails
    2.08
     TAIL
    2.02
    TAIL
    1.90
    tails
    1.88
     Tails
    1.73
    Tails
    1.73
    Activations Density 0.187%

    No Known Activations