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. 2-GEMMASCOPE-RES-16K
    6. 6185
    Prev
    Next
    INDEX
    Explanations

    mathematical structures, particularly arrays and their alignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ratulations
    -0.69
     DBNull
    -0.61
    spunkt
    -0.59
    }{$
    -0.59
    outube
    -0.58
    ulex
    -0.56
    horror
    -0.56
    তথ্যসূত্র
    -0.56
    clearpage
    -0.56
    memcmp
    -0.55
    POSITIVE LOGITS
    array
    3.11
     array
    2.16
     arrays
    1.63
    arrays
    1.51
    ARRAY
    1.33
     ARRAY
    1.17
    数组
    1.15
     Arrays
    1.10
    mtable
    1.03
    asarray
    1.01
    Activations Density 0.079%

    No Known Activations