© 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. 0-GEMMASCOPE-RES-16K
    11. 10066
    Prev
    Next
    INDEX
    Explanations

    the term "afford," indicating a focus on financial capability and constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.95
     مشين
    -0.93
     Efq
    -0.83
     depositphotos
    -0.82
     Majefty
    -0.81
     uſed
    -0.81
    ſelf
    -0.81
     ſtand
    -0.79
     poffible
    -0.78
    newswire
    -0.78
    POSITIVE LOGITS
     afford
    0.83
    afford
    0.60
     ke
    0.60
     suicide
    0.56
     tre
    0.56
     distinct
    0.53
    UrlEncoded
    0.51
     affor
    0.51
    tre
    0.49
     Suicide
    0.49
    Activations Density 0.130%

    No Known Activations