© 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 EvalsExportsAPI 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. 9454
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or section

    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
    -0.67
     متعلقه
    -0.63
     CURIAM
    -0.58
     Ráp
    -0.58
    loride
    -0.55
    @[+][
    -0.55
    pins
    -0.54
    bių
    -0.53
     postale
    -0.53
     Boswell
    -0.53
    POSITIVE LOGITS
     MonoBehaviour
    1.11
     UnityEngine
    1.07
     TMPro
    0.89
    PreInfinity
    0.72
     UnityEditor
    0.72
    IBOutlet
    0.70
    randomUUID
    0.66
    SerializeField
    0.65
     GenerationType
    0.64
     WaitForSeconds
    0.63
    Activations Density 0.116%

    No Known Activations