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. 15897
    Prev
    Next
    INDEX
    Explanations

    terms related to data retrieval and absence in scientific contexts

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

    Comes before "from"

    np_acts-logits-general · gemini-2.0-flash

    derived from or away from

    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
    ضة
    -0.65
    zez
    -0.64
    ึ้น
    -0.62
     tình
    -0.59
    ließlich
    -0.59
    nerie
    -0.58
    CardContent
    -0.58
    orei
    -0.56
    quién
    -0.56
    Външни
    -0.55
    POSITIVE LOGITS
     from
    1.48
     therefrom
    1.28
    from
    1.20
     khỏi
    1.14
     FROM
    1.05
    From
    0.93
    จาก
    0.93
    FROM
    0.92
    Away
    0.91
     Away
    0.90
    Activations Density 0.471%

    No Known Activations