© 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. 2669
    Prev
    Next
    INDEX
    Explanations

    instances of hard work and effort in various contexts

    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
     ComVisible
    -0.63
     Offisielt
    -0.58
    ///</
    -0.56
    VersionUID
    -0.55
    GIVEREF
    -0.55
     transfieras
    -0.55
     الاطلاع
    -0.54
    IntoConstraints
    -0.54
     validamos
    -0.54
    XmlAccessorType
    -0.54
    POSITIVE LOGITS
     hard
    2.65
    hard
    2.09
     HARD
    1.97
     harder
    1.86
    Hard
    1.83
     Hard
    1.83
    HARD
    1.81
     hardest
    1.66
     Harder
    1.37
     harde
    1.33
    Activations Density 0.362%

    No Known Activations