© 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. 6-GEMMASCOPE-RES-16K
    11. 2863
    Prev
    Next
    INDEX
    Explanations

    functions and methods related to string manipulation, particularly those that adjust case or manage substrings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    적으로
    -0.55
    lardan
    -0.52
    >')
    -0.52
     entre
    -0.50
    diğimiz
    -0.50
     sở
    -0.49
    켜
    -0.47
    هام
    -0.46
    Disco
    -0.45
     McKin
    -0.44
    POSITIVE LOGITS
    ThroughAttribute
    1.20
    PerformLayout
    1.06
     مشين
    1.04
    randomUUID
    1.03
     للمعارف
    1.01
    fetchone
    0.96
    fetchall
    0.92
    NewGuid
    0.90
    EndInit
    0.88
    InputBorder
    0.88
    Activations Density 0.141%

    No Known Activations