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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39005
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to mathematical and scientific structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ResourceId
    -0.39
    戒
    -0.38
    ies
    -0.38
     cue
    -0.37
    вобо
    -0.36
    IES
    -0.35
     top
    -0.35
    hie
    -0.35
    uar
    -0.35
    crit
    -0.34
    POSITIVE LOGITS
    +#+#
    0.90
    ChildScrollView
    0.88
     referenties
    0.88
     GenerationType
    0.85
    Билгалдахарш
    0.84
     estimés
    0.81
     &___
    0.78
    MessageOf
    0.75
    annica
    0.74
    Scénario
    0.73
    Activations Density 0.302%

    No Known Activations