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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 4503
    Prev
    Next
    INDEX
    Explanations

    code-related terms and operations, particularly those pertaining to function definitions and variable manipulations

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

    Code snippets found in Javascript or potentially other languages

    np_acts-logits-general · gemini-2.0-flash

    code blocks and syntax

    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
     صوتيه
    -0.99
     كومونز
    -0.95
    ็จ
    -0.92
     مرئيه
    -0.89
    
    -0.88
    ArgsConstructor
    -0.88
     AttributeSet
    -0.87
    TagHelper
    -0.85
     للمعارف
    -0.84
     تانيه
    -0.84
    POSITIVE LOGITS
    9
    0.55
                
    0.53
    ↵
    0.44
     man
    0.41
     ısı
    0.40
     mans
    0.39
    <strong>
    0.38
    ↵↵
    0.36
    *
    0.36
    1
    0.36
    Activations Density 0.046%

    No Known Activations