© 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. 7139
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related terms, particularly focusing on percentages and ranges

    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
    47
    +0.12
    0.4%
    1978
    +0.10
    0.3%
    893
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.12
    0.06
    776
    +0.10
    0.05
    499
    +0.10
    0.04
    Negative Logits
     reluct
    -1.27
     shenan
    -1.20
     gaily
    -1.09
     encomp
    -1.09
     emphat
    -1.07
     accla
    -1.05
     sophistic
    -1.03
     Daven
    -1.02
     apprehen
    -1.02
     affor
    -1.01
    POSITIVE LOGITS
    9
    0.54
    8
    0.50
     tena
    0.50
    3
    0.49
    5
    0.48
    equila
    0.48
    6
    0.47
    2
    0.47
    льника
    0.46
    7
    0.46
    Activations Density 0.210%

    No Known Activations