Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 9858
    Prev
    Next
    INDEX
    Explanations

    programming languages and their specific frameworks or libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raiſ
    -0.60
    Distribuzione
    -0.57
    chiat
    -0.57
     gezien
    -0.57
    resizingMask
    -0.56
    MarshalTo
    -0.56
    ArgsConstructor
    -0.55
     whoſe
    -0.55
    колко
    -0.54
    flich
    -0.54
    POSITIVE LOGITS
    ########.
    1.22
     UnityEngine
    0.91
    Xna
    0.85
    nestjs
    0.75
    BASEPATH
    0.75
    providedIn
    0.73
    脚注の使い方
    0.67
     SwiftUI
    0.65
     UIKit
    0.64
    OrNil
    0.63
    Activations Density 0.087%

    No Known Activations