© 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. 7181
    Prev
    Next
    INDEX
    Explanations

    economic terms and concepts

    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
    1013
    +0.10
    0.3%
    227
    +0.10
    0.3%
    1299
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    342
    +0.10
    0.06
    1867
    +0.10
    0.05
    1095
    +0.09
    0.04
    Negative Logits
     écout
    -1.39
     véhic
    -1.38
     fep
    -1.35
     décid
    -1.33
     récomp
    -1.32
     ftu
    -1.28
     prét
    -1.25
     mef
    -1.25
     fta
    -1.24
     secon
    -1.23
    POSITIVE LOGITS
     whose
    1.22
    whose
    0.96
     who
    0.95
     that
    0.82
     which
    0.79
     capable
    0.78
     with
    0.74
     whom
    0.74
     unable
    0.72
     requiring
    0.72
    Activations Density 0.448%

    No Known Activations