© 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. 13291
    Prev
    Next
    INDEX
    Explanations

    instructions on procedures or items

    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
    1331
    +0.13
    0.4%
    1520
    +0.12
    0.4%
    1763
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    624
    +0.13
    0.03
    736
    +0.12
    0.04
    1363
    +0.11
    0.03
    Negative Logits
     cabrio
    -0.84
     migli
    -0.82
     oreo
    -0.80
     Keny
    -0.79
     Basili
    -0.79
     vespa
    -0.79
     hairc
    -0.77
     expéri
    -0.74
     Senat
    -0.74
     eyel
    -0.74
    POSITIVE LOGITS
     balloon
    0.91
     inflate
    0.89
     balloons
    0.88
     inflated
    0.87
     inflation
    0.83
    balloon
    0.76
     rubber
    0.75
     inflatable
    0.74
    inflate
    0.74
    inflation
    0.72
    Activations Density 0.197%

    No Known Activations