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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 8143
    Prev
    Next
    INDEX
    Explanations

    terms related to construction and engineering elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.89
    tanleria
    -0.83
     JpaRepository
    -0.82
    তথ্যসূত্র
    -0.81
    oredCriteria
    -0.79
     <=",
    -0.78
     '\\;'
    -0.77
     урна
    -0.76
    Personendaten
    -0.74
    èdia
    -0.73
    POSITIVE LOGITS
    zog
    0.55
     نسبة
    0.53
    ц
    0.52
    jsp
    0.49
    כ
    0.49
     trámites
    0.49
    yp
    0.49
     lunghi
    0.48
    yth
    0.48
     goto
    0.48
    Activations Density 2.258%

    No Known Activations