Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 11103
    Prev
    Next
    INDEX
    Explanations

    elements related to political discourse and social critique

    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
     feroit
    -0.75
     Audiodateien
    -0.74
     auroit
    -0.74
     étoit
    -0.72
     avoient
    -0.72
     étoient
    -0.69
    cookieParser
    -0.67
    ]-->
    -0.67
     inmediata
    -0.67
     alltid
    -0.67
    POSITIVE LOGITS
     decent
    1.45
     decently
    1.25
     semblance
    1.24
     tolerable
    1.16
     reasonable
    1.14
     respectable
    1.14
     reasonably
    1.14
     vaguely
    1.12
     halb
    1.11
     worthwhile
    1.06
    Activations Density 0.650%

    No Known Activations