© 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. 2229
    Prev
    Next
    INDEX
    Explanations

    examples and instances within a text

    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
    752
    +0.17
    0.5%
    68
    +0.10
    0.3%
    1129
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.17
    0.04
    68
    +0.10
    0.02
    752
    +0.09
    0.03
    Negative Logits
    !("{
    -0.69
    <bos>
    -0.68
    umacher
    -0.64
    تفصیلات
    -0.59
    Preliminaries
    -0.55
    roek
    -0.53
    參考文獻
    -0.52
    Související
    -0.50
    mặt
    -0.50
     Allociné
    -0.50
    POSITIVE LOGITS
     santiago
    0.92
     palab
    0.82
     napoli
    0.81
     tenerife
    0.80
     cristina
    0.79
     alicante
    0.79
     valencia
    0.78
     juventus
    0.76
     cordoba
    0.76
     barcelona
    0.75
    Activations Density 0.146%

    No Known Activations