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. 2-GEMMASCOPE-RES-16K
    6. 3617
    Prev
    Next
    INDEX
    Explanations

    mentions of inventory and observations related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     {}));
    -0.63
    intellij
    -0.62
     =>'
    -0.60
    ;#
    -0.59
    basicConfig
    -0.56
    диод
    -0.55
     Lizzy
    -0.53
    Chapitre
    -0.52
     Hra
    -0.52
     unwra
    -0.52
    POSITIVE LOGITS
     desperate
    0.83
    usercontent
    0.77
    enumi
    0.72
     desperation
    0.70
    Stand
    0.70
     observations
    0.69
     Observation
    0.69
    ymce
    0.68
     Observations
    0.67
    /*
    0.67
    Activations Density 0.095%

    No Known Activations