© 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. 13363
    Prev
    Next
    INDEX
    Explanations

    phrases related to quotations and statements

    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
    1008
    +0.08
    0.2%
    284
    +0.08
    0.2%
    792
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.08
    0.06
    62
    +0.08
    0.04
    1925
    +0.07
    0.04
    Negative Logits
     unlaw
    -1.28
     encomp
    -1.21
     guarante
    -1.21
     reluct
    -1.20
     ftu
    -1.18
     accla
    -1.18
     volunte
    -1.18
     fte
    -1.17
     maneu
    -1.17
     sovere
    -1.17
    POSITIVE LOGITS
    ioutil
    0.63
    <bos>
    0.62
     regarding
    0.61
    audiovisuel
    0.61
    aughey
    0.60
    ariConfig
    0.59
    Nazionale
    0.58
    鍮
    0.57
     about
    0.55
    ollection
    0.54
    Activations Density 0.292%

    No Known Activations