© 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. 14385
    Prev
    Next
    INDEX
    Explanations

    strings of characters that are possibly related to computer programming or technical operations

    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
    +0.20
    0.6%
    1108
    +0.10
    0.3%
    1870
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.20
    0.04
    1108
    +0.10
    0.03
    1322
    +0.09
    0.02
    Negative Logits
    ohist
    -0.58
     post
    -0.51
     from
    -0.50
     I
    -0.50
    的数量
    -0.48
     over
    -0.48
     and
    -0.48
     about
    -0.47
     for
    -0.47
     (
    -0.47
    POSITIVE LOGITS
     quæ
    1.17
     ananas
    1.15
     marte
    1.13
     napoli
    1.13
     sappi
    1.10
     sement
    1.09
     siena
    1.08
     meis
    1.06
     milano
    1.05
     habet
    1.05
    Activations Density 0.050%

    No Known Activations