© 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. 8815
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or difficulty in understanding

    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
     виправивши
    -0.69
     CreateTagHelper
    -0.54
    JNIEnv
    -0.53
    yntaxException
    -0.53
    styleType
    -0.51
    ArrowToggle
    -0.51
    Rhestr
    -0.51
     ObjectParameter
    -0.49
    verwijspagina
    -0.49
    featureID
    -0.49
    POSITIVE LOGITS
     read
    3.43
     reading
    2.91
     reads
    2.80
    read
    2.77
     Read
    2.53
     READ
    2.42
    Read
    2.33
    reading
    2.30
     Reads
    2.20
     Reading
    2.19
    Activations Density 0.692%

    No Known Activations