© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 9048
    Prev
    Next
    INDEX
    Explanations

    references to programming-related frameworks and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ment
    -0.52
    FirstResponder
    -0.51
     Manley
    -0.51
    :+:
    -0.51
     Spéc
    -0.48
     UnityEngine
    -0.48
     viewDidLoad
    -0.47
     avanti
    -0.47
    StructField
    -0.47
     lontano
    -0.47
    POSITIVE LOGITS
     ISBN
    1.40
    ISBN
    1.20
     CreateTagHelper
    1.18
     ISSN
    1.02
     AssemblyTitle
    1.00
    SerializedName
    1.00
    matchCondition
    0.89
     isbn
    0.88
    ISSN
    0.84
    imageshack
    0.83
    Activations Density 0.005%

    No Known Activations