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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6329
    Prev
    Next
    INDEX
    Explanations

    numerical data related to recalls or automotive information

    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
    principalTable
    -0.79
    zegor
    -0.76
    enterOuterAlt
    -0.68
    دانشنامهٔ
    -0.68
     AssemblyCulture
    -0.65
    égard
    -0.65
     végét
    -0.65
    étoit
    -0.65
     propOrder
    -0.65
    matchCondition
    -0.64
    POSITIVE LOGITS
    HostException
    0.54
    endphp
    0.54
    TargetException
    0.51
    fetchall
    0.50
    spaceBetween
    0.50
     estekak
    0.49
    |()
    0.49
    ↵↵
    0.48
    fetchone
    0.48
    pear
    0.47
    Activations Density 0.243%

    No Known Activations