© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 11911
    Prev
    Next
    INDEX
    Explanations

    token sequences containing a mix of numbers and letters in a certain pattern

    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
    1343
    +0.27
    0.9%
    876
    +0.24
    0.7%
    1842
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.27
    0.04
    295
    +0.24
    0.02
    185
    +0.13
    0.03
    Negative Logits
     unspeak
    -0.87
     very
    -0.78
     Cruces
    -0.77
     impelled
    -0.77
    要么
    -0.74
    cedula
    -0.73
    的数量
    -0.73
     and
    -0.71
     most
    -0.71
     the
    -0.71
    POSITIVE LOGITS
     mef
    2.02
     illi
    2.01
     effe
    1.93
     igno
    1.91
     wien
    1.89
     sappi
    1.89
     blos
    1.88
     sii
    1.88
     oner
    1.87
     franz
    1.87
    Activations Density 0.053%

    No Known Activations