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. 10-GEMMASCOPE-RES-16K
    6. 12408
    Prev
    Next
    INDEX
    Explanations

    references to loyalty, support, and positions in the context of historical conflicts, particularly relating to different factions or causes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntentFilter
    -0.69
    ]")]
    -0.60
    ENODEV
    -0.60
    '},
    
    -0.57
    ",&
    -0.57
    }],
    
    -0.57
    antMatchers
    -0.56
    +#+#
    -0.55
     JpaRepository
    -0.54
    }")]
    -0.54
    POSITIVE LOGITS
     laikā
    0.51
     Majesté
    0.48
     AllMovie
    0.47
     sebaliknya
    0.47
     versus
    0.47
     Versus
    0.46
     stay
    0.46
    farin
    0.45
     geslacht
    0.44
     whichever
    0.44
    Activations Density 0.804%

    No Known Activations