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. 25-GEMMASCOPE-RES-16K
    6. 4444
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving advice or making recommendations

    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
    transQ
    -0.62
    Datuak
    -0.54
    ⓧ
    -0.52
    hyrchwyd
    -0.50
    triangleq
    -0.50
     HDR
    -0.49
     Mawr
    -0.49
    })->
    -0.49
     &___
    -0.49
    Географиясе
    -0.48
    POSITIVE LOGITS
     Russian
    1.08
     RUSS
    1.02
    Russian
    0.98
     Russia
    0.93
     Russians
    0.91
     Moscow
    0.91
    Moscow
    0.89
    Russia
    0.89
     russischen
    0.81
     Moscou
    0.81
    Activations Density 0.005%

    No Known Activations