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. 24-GEMMASCOPE-RES-16K
    6. 4491
    Prev
    Next
    INDEX
    Explanations

    instances of specific numeric or technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related closing syntax

    np_acts-logits-general · gemini-2.0-flash

    availability, adjusts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ),
    
    -0.59
     ");
    
    -0.55
     })
    
    -0.55
     ")
    
    -0.49
     both
    -0.47
    '],
    
    -0.46
     ),
    -0.46
    ore
    -0.46
     )$
    -0.46
    "),
    
    -0.45
    POSITIVE LOGITS
    }
    0.84
     AssemblyCulture
    0.82
    featureID
    0.80
     виправивши
    0.80
    WebVitals
    0.79
    InstanceState
    0.73
    CppMethod
    0.72
     Roskov
    0.72
    EndGlobalSection
    0.72
     Exactos
    0.70
    Activations Density 0.042%

    No Known Activations