© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2502
    Prev
    Next
    INDEX
    Explanations

    phrases related to mathematical instructions and procedures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    732
    +0.14
    0.6%
    2011
    +0.13
    0.5%
    1271
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    732
    +0.14
    0.04
    1044
    +0.13
    0.04
    1451
    +0.13
    0.03
    Negative Logits
    sproz
    -0.54
    vece
    -0.50
     laude
    -0.48
    Inoltre
    -0.47
     Leinwand
    -0.46
    AddWithValue
    -0.46
    ohist
    -0.45
     CURLOPT
    -0.44
     guma
    -0.44
    BooleanField
    -0.43
    POSITIVE LOGITS
     Order
    1.18
     Orders
    1.14
     order
    1.13
     shenan
    1.12
     getOrder
    1.11
     Ordering
    1.11
     orders
    1.08
    order
    1.08
     reordered
    1.07
     ordering
    1.04
    Activations Density 0.102%

    No Known Activations