© 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. 6853
    Prev
    Next
    INDEX
    Explanations

    phrases related to procedures or steps in a process

    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
    453
    +0.12
    0.3%
    690
    +0.09
    0.3%
    1978
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    353
    +0.12
    0.02
    946
    +0.09
    0.03
    310
    +0.09
    0.02
    Negative Logits
     disagre
    -2.42
     volunte
    -2.37
     increa
    -2.34
     reluct
    -2.33
     shenan
    -2.28
     impra
    -2.26
     maneu
    -2.22
     encomp
    -2.22
     depic
    -2.21
     philanth
    -2.18
    POSITIVE LOGITS
     she
    0.87
     he
    0.85
    she
    0.83
     they
    0.82
     Obrador
    0.82
     you
    0.81
     it
    0.78
     him
    0.77
    TextHelper
    0.75
    我
    0.75
    Activations Density 0.150%

    No Known Activations