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. 3-GEMMASCOPE-RES-16K
    6. 16317
    Prev
    Next
    INDEX
    Explanations

    terms related to data file operations and memory management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -1.10
    InjectAttribute
    -1.04
    __':
    
    -1.01
     Audiodateien
    -0.99
    AutoScaleMode
    -0.99
     }}"></
    -0.99
    KommentareTeilen
    -0.97
    LookAnd
    -0.93
     "..\..\..\
    -0.92
     مرئيه
    -0.92
    POSITIVE LOGITS
    .
    0.58
     of
    0.52
    ,
    0.51
     to
    0.47
     a
    0.47
    ary
    0.47
     I
    0.47
    fseek
    0.47
     position
    0.46
     i
    0.46
    Activations Density 0.555%

    No Known Activations