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. 22-GEMMASCOPE-RES-16K
    6. 15643
    Prev
    Next
    INDEX
    Explanations

    elements related to error handling and data parsing in code

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

    Objective-C type checking

    np_acts-logits-general · gemini-2.0-flash

    Objective-C class checking and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.50
    Arri
    -0.49
     jang
    -0.49
     BorderRadius
    -0.48
    completion
    -0.43
    acyjna
    -0.42
     muerto
    -0.42
     Gallimard
    -0.41
    rinol
    -0.41
     Arri
    -0.41
    POSITIVE LOGITS
    الحياه
    0.81
    
    0.65
    Tikang
    0.63
    ########.
    0.60
     tartalomajánló
    0.60
     transfieras
    0.59
    }());
    0.58
    Portale
    0.58
     performance
    0.58
     versa
    0.57
    Activations Density 0.192%

    No Known Activations