© 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. 25-GEMMASCOPE-RES-16K
    11. 3242
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.76
     rospy
    -0.60
    StoreMessageInfo
    -0.58
    脚注の使い方
    -0.58
    IsMutable
    -0.56
     CURIAM
    -0.54
    новништво
    -0.50
    EndGlobalSection
    -0.50
     defaultstate
    -0.50
    ThroughAttribute
    -0.49
    POSITIVE LOGITS
     never
    3.36
    never
    2.79
     Never
    2.73
    Never
    2.66
     NEVER
    2.36
     nunca
    2.33
     nigdy
    2.22
    NEVER
    2.19
     nooit
    2.10
     aldri
    2.05
    Activations Density 0.467%

    No Known Activations