© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 11551
    Prev
    Next
    INDEX
    Explanations

    words indicating personal experiences and emotions related to self-discovery and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzleHttp
    -0.89
    MigrationBuilder
    -0.73
    abstractmethod
    -0.61
    يميديا
    -0.61
    principalTable
    -0.60
     للمعارف
    -0.60
    ContextHolder
    -0.59
     الحره
    -0.59
    UnsafeEnabled
    -0.59
    setupUi
    -0.58
    POSITIVE LOGITS
     realized
    2.32
     realised
    2.14
     realize
    2.13
     realizes
    2.08
     realization
    2.01
     realizing
    1.99
     realise
    1.96
     discovered
    1.96
     realises
    1.88
     realising
    1.84
    Activations Density 0.531%

    No Known Activations