© 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. 13477
    Prev
    Next
    INDEX
    Explanations

    quotes and reported speech

    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
    1252
    +0.12
    0.3%
    946
    +0.11
    0.3%
    194
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.12
    0.06
    1252
    +0.11
    0.05
    1551
    +0.10
    0.04
    Negative Logits
     namorados
    -0.68
     parlano
    -0.66
    readObject
    -0.65
     meninos
    -0.61
     parlar
    -0.61
    HasAnnotation
    -0.60
     Paglinawan
    -0.60
    rinfo
    -0.60
     casais
    -0.59
    Sucesor
    -0.59
    POSITIVE LOGITS
     McLaugh
    1.03
     reluct
    0.85
     apprehen
    0.84
     members
    0.83
     Shakspeare
    0.83
     Bartholo
    0.82
     Vaugh
    0.81
     Juf
    0.81
     groupName
    0.81
     group
    0.80
    Activations Density 0.760%

    No Known Activations