© 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. 3945
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of reviews

    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
    866
    +0.12
    0.5%
    437
    +0.11
    0.4%
    1677
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    866
    +0.12
    0.02
    1677
    +0.11
    0.03
    1971
    +0.11
    0.02
    Negative Logits
     Bartholo
    -0.66
     solidar
    -0.62
     pixabay
    -0.61
     Hermans
    -0.60
     Rodrig
    -0.59
     Molière
    -0.58
     Gorb
    -0.57
     Strukt
    -0.57
     instan
    -0.57
     Ibidem
    -0.56
    POSITIVE LOGITS
     review
    1.30
    review
    1.26
     reviews
    1.21
     Review
    1.18
    Review
    1.14
    reviews
    1.13
     REVIEW
    1.12
     reviewed
    1.08
     Reviews
    1.05
    REVIEW
    1.01
    Activations Density 0.079%

    No Known Activations