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. 3724
    Prev
    Next
    INDEX
    Explanations

    terms related to Earth and its various aspects

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

    following "Earth," "nation," "world," or "year"

    np_acts-logits-general · gemini-2.0-flash

    Earth, world, year, tonight

    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
    ?}",
    -0.49
    WithIOException
    -0.46
     altezza
    -0.43
    TypedDataSet
    -0.42
    󠁢
    -0.41
     hidráulica
    -0.40
    jewództ
    -0.40
    ),"
    -0.40
    },'
    -0.39
     Guille
    -0.39
    POSITIVE LOGITS
     Majefty
    0.58
    ClientRect
    0.47
    randomUUID
    0.47
    こち
    0.42
    archi
    0.42
    weakSelf
    0.42
    kään
    0.41
    ButterKnife
    0.41
    Personendaten
    0.41
     iprot
    0.40
    Activations Density 0.541%

    No Known Activations