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. 16-GEMMASCOPE-RES-16K
    6. 1875
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions related to calculation and evaluation

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

    Comes before or after filename or equation

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -1.07
    DockStyle
    -1.01
    tagHelperRunner
    -0.98
    __':
    
    -0.96
     protoimpl
    -0.87
    TypedDataSet
    -0.86
    Архівовано
    -0.85
    principalColumn
    -0.84
    OGND
    -0.83
    存于互联网档案馆
    -0.81
    POSITIVE LOGITS
    .
    1.91
    %.
    1.04
    。
    1.02
    ().
    1.01
    ).
    1.00
    '.
    0.99
    *.
    0.98
    ".
    0.93
    ».
    0.93
    }.
    0.93
    Activations Density 1.006%

    No Known Activations