© 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. 12638
    Prev
    Next
    INDEX
    Explanations

    quotes and excerpts from longer text or conversations

    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
    2019
    +0.23
    0.7%
    924
    +0.13
    0.4%
    605
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.23
    0.10
    545
    +0.13
    0.08
    2019
    +0.12
    0.09
    Negative Logits
    Awkward
    -0.62
     ecru
    -0.62
    Fuckin
    -0.61
    Cringe
    -0.61
    Bullshit
    -0.59
     cushi
    -0.57
    Hilarious
    -0.57
    Ahem
    -0.57
     velour
    -0.57
     steed
    -0.56
    POSITIVE LOGITS
    heyd
    0.72
    ”“
    0.69
    “-
    0.67
    kese
    0.65
    ventus
    0.64
    <bos>
    0.63
     ambientale
    0.62
    “:
    0.61
     torba
    0.60
     trast
    0.60
    Activations Density 0.397%

    No Known Activations