© 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. 22-GEMMASCOPE-RES-16K
    6. 13155
    Prev
    Next
    INDEX
    Explanations

    elements indicative of programming and documentation syntax

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

    LaTeX and programming code

    np_acts-logits-general · gemini-2.0-flash

    arhaic spellings, punctuation

    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
     defaultstate
    -1.11
    XmlAccessType
    -0.87
     صوتيه
    -0.85
    NOPQRST
    -0.84
    CppMethod
    -0.81
    IntoConstraints
    -0.81
    GOTREF
    -0.81
    ImageContext
    -0.79
     nonatomic
    -0.75
     AssemblyCulture
    -0.75
    POSITIVE LOGITS
    }}}
    
    0.70
     »)
    0.66
     myſelf
    0.60
    .";
    
    0.60
    )))
    
    0.59
    .,"
    0.57
     )
    0.56
     againſt
    0.56
     itſelf
    0.56
    )';
    0.56
    Activations Density 2.963%

    No Known Activations