© 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. 13411
    Prev
    Next
    INDEX
    Explanations

    timestamps in a description of a sequence of events

    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
    908
    +0.11
    0.3%
    2010
    +0.08
    0.2%
    690
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    908
    +0.11
    0.02
    2010
    +0.08
    0.04
    1859
    +0.08
    0.03
    Negative Logits
     disagre
    -1.53
     maneu
    -1.53
     indestru
    -1.44
     affor
    -1.43
     scrat
    -1.42
     shenan
    -1.41
     reluct
    -1.41
     strick
    -1.41
     snoopy
    -1.40
     excru
    -1.38
    POSITIVE LOGITS
     quick
    1.33
     quickly
    1.33
     fast
    1.27
     rapid
    1.25
     quicker
    1.20
     faster
    1.19
     rapidly
    1.12
    fast
    1.09
     instant
    1.09
     nhanh
    1.06
    Activations Density 0.568%

    No Known Activations