© 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. 18-GEMMASCOPE-RES-16K
    6. 1237
    Prev
    Next
    INDEX
    Explanations

    specific programming terms and references related to data structures, classes, and methods

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

    Tokens before punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    math and programming notation

    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
    )++;
    -0.82
    ']);
    
    -0.67
    ]--;
    -0.67
    écial
    -0.64
     }}"></
    -0.63
    >--}}
    -0.62
    '][$
    -0.62
    ']],
    -0.60
    }}],
    -0.60
    '],$
    -0.59
    POSITIVE LOGITS
    URLException
    0.65
    ruptedException
    0.64
    .
    0.61
    ValueGeneration
    0.60
    ChildScrollView
    0.58
    +#+#
    0.58
    ArgsConstructor
    0.57
     Humanos
    0.57
    OwnProperty
    0.57
    dataclass
    0.56
    Activations Density 0.534%

    No Known Activations