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. 14-GEMMASCOPE-RES-16K
    6. 10820
    Prev
    Next
    INDEX
    Explanations

    terms related to foundational concepts or parameters in systems and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PushMatrix
    -0.61
     a
    -0.50
     tanta
    -0.50
     is
    -0.49
     fiducia
    -0.48
     with
    -0.46
     at
    -0.46
    もの
    -0.46
     also
    -0.46
     in
    -0.44
    POSITIVE LOGITS
    IContainer
    0.88
    ^(@)
    0.86
     part
    0.76
     beginnetje
    0.74
    <?
    0.74
    ⓧ
    0.73
    niest
    0.71
     елның
    0.69
     periphery
    0.68
     parts
    0.68
    Activations Density 0.466%

    No Known Activations