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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 12423
    Prev
    Next
    INDEX
    Explanations

    terms related to development and changes in systems or processes

    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
    المناصب
    -0.62
    )";
    
    -0.57
    }))
    
    -0.55
    igshid
    -0.54
     توانند
    -0.54
    )="
    -0.51
     intptr
    -0.50
    }));
    
    -0.49
    égard
    -0.48
    seteq
    -0.48
    POSITIVE LOGITS
     atsi
    0.62
     ujednoznacz
    0.59
    ConstraintMaker
    0.59
     Existence
    0.54
    NgModule
    0.54
    pherals
    0.54
     externi
    0.53
    يكب
    0.53
     poveznice
    0.52
     विश्वसनीयता
    0.51
    Activations Density 1.197%

    No Known Activations