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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 15454
    Prev
    Next
    INDEX
    Explanations

    references to the need for further research and investigation in various studies

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

    "Is/are" followed by words indicating a need or requirement

    np_acts-logits-general · gemini-2.0-flash

    is/are needed/required

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     مُعرِّف
    -0.65
     SIMBAD
    -0.52
     üzere
    -0.50
     personnalisée
    -0.47
    ifiquement
    -0.46
    تفصیلات
    -0.46
    accepts
    -0.46
    IBOutlet
    -0.46
    styleType
    -0.45
    omorphic
    -0.44
    POSITIVE LOGITS
     required
    2.38
     necessary
    2.16
     needed
    2.13
    required
    2.10
     Required
    2.09
    Required
    1.95
     REQUIRED
    1.85
     Needed
    1.83
    necessary
    1.79
     Necessary
    1.77
    Activations Density 0.471%

    No Known Activations