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. 18-GEMMASCOPE-RES-16K
    6. 3633
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and programming constructs, particularly error handling and assembly attributes

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

    or phrases followed by parentheses

    np_acts-logits-general · gemini-2.0-flash

    code identifiers and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.58
    ară
    -0.58
    anyahu
    -0.56
    riwal
    -0.55
    Становништво
    -0.53
    TextNode
    -0.53
    InstanceState
    -0.51
     optik
    -0.50
    
    -0.49
    COLN
    -0.49
    POSITIVE LOGITS
     ModelExpression
    1.30
    webElementXpaths
    1.19
     تضيفلها
    1.17
    Personensuche
    1.17
    UnusedPrivate
    1.12
    "}";
    1.04
    BibitemShut
    1.03
    LookAnd
    1.01
    )";
    
    1.00
    ]})
    1.00
    Activations Density 0.367%

    No Known Activations