© 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. 4422
    Prev
    Next
    INDEX
    Explanations

    dollar amounts mentioned in a document

    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
    1978
    +0.13
    0.4%
    1265
    +0.11
    0.4%
    1177
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1935
    +0.13
    0.05
    573
    +0.11
    0.05
    1077
    +0.10
    0.05
    Negative Logits
     unspeak
    -0.93
     intersper
    -0.83
     intrigu
    -0.81
     snoopy
    -0.81
     melange
    -0.81
     celtic
    -0.78
     indescri
    -0.77
     shenan
    -0.76
     jurassic
    -0.76
     nordic
    -0.75
    POSITIVE LOGITS
     utop
    1.35
     ananas
    1.35
     silikon
    1.29
     Ottobre
    1.22
     kafe
    1.21
     Luglio
    1.19
     benzin
    1.19
     torba
    1.18
     Giugno
    1.18
     karton
    1.16
    Activations Density 0.094%

    No Known Activations