© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 13717
    Prev
    Next
    INDEX
    Explanations

    phrases related to questioning and answers in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }$​
    -0.83
     transfieras
    -0.81
    glClear
    -0.78
    DoubleQuotes
    -0.76
    MessageOf
    -0.76
     maer
    -0.73
     Majefty
    -0.73
    __()
    -0.73
    aarrggbb
    -0.72
     Monfieur
    -0.72
    POSITIVE LOGITS
     too
    0.47
    webElementXpaths
    0.47
     tanggung
    0.44
     delin
    0.43
    log
    0.42
     potentially
    0.41
    命的
    0.41
     trekken
    0.41
     bertanggung
    0.40
    .
    0.40
    Activations Density 0.383%

    No Known Activations