© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3867
    Prev
    Next
    INDEX
    Explanations

    numerical values or terms related to numbers

    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
    537
    +0.13
    0.5%
    1363
    +0.12
    0.5%
    1101
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.13
    0.04
    755
    +0.12
    0.04
    1101
    +0.11
    0.03
    Negative Logits
     morire
    -0.69
     dovr
    -0.69
     maksi
    -0.68
     rendono
    -0.68
     lancia
    -0.68
     držav
    -0.65
     italia
    -0.65
     vivace
    -0.65
     sopr
    -0.64
     „,
    -0.63
    POSITIVE LOGITS
     number
    1.17
     numbers
    1.15
    number
    1.08
    numbers
    1.01
     Number
    1.01
    Number
    0.99
     num
    0.99
    getNumber
    0.96
     getNumber
    0.96
    Numbers
    0.95
    Activations Density 0.086%

    No Known Activations