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. 15-GEMMASCOPE-RES-16K
    6. 8791
    Prev
    Next
    INDEX
    Explanations

    terms associated with the concept of elevation or increase

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    polation
    -1.03
    BibitemShut
    -0.99
    tershire
    -0.96
    theless
    -0.94
    redient
    -0.93
    ization
    -0.93
     Ceci
    -0.91
    modity
    -0.91
    ized
    -0.88
    Viki
    -0.88
    POSITIVE LOGITS
    -
    0.80
    k
    0.80
    Off
    0.76
    r
    0.76
    w
    0.76
     Off
    0.75
    z
    0.73
    Out
    0.73
     Down
    0.71
     Out
    0.70
    Activations Density 0.130%

    No Known Activations