© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 4568
    Prev
    Next
    INDEX
    Explanations

    quotes or passages containing the word "and"

    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
    604
    +0.17
    0.5%
    50
    +0.10
    0.3%
    1553
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1806
    +0.17
    0.06
    1224
    +0.10
    0.06
    1265
    +0.09
    0.04
    Negative Logits
    <bos>
    -1.29
     kompati
    -0.91
     kön
    -0.87
     karton
    -0.84
     prétend
    -0.82
     kupa
    -0.81
     déchir
    -0.81
     alkoh
    -0.81
     perpé
    -0.80
    StoreMessageInfo
    -0.79
    POSITIVE LOGITS
     pymysql
    0.66
     incomplete
    0.64
     inadequate
    0.63
     lacking
    0.61
     inconsistent
    0.60
     lacks
    0.59
     newArr
    0.57
     unpredictable
    0.57
     insufficient
    0.57
     unusable
    0.57
    Activations Density 0.355%

    No Known Activations