© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5509
    Prev
    Next
    INDEX
    Explanations

    phrases related to events and locations

    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
    1527
    +0.09
    0.3%
    674
    +0.07
    0.2%
    478
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    839
    +0.09
    0.03
    71
    +0.07
    0.03
    1001
    +0.07
    0.03
    Negative Logits
     hcm
    -1.29
     anton
    -1.27
     Mémoires
    -1.25
     Sén
    -1.24
     Cfr
    -1.23
     Traité
    -1.23
     centrif
    -1.22
     mef
    -1.21
     milano
    -1.19
     Mâ
    -1.18
    POSITIVE LOGITS
     nonetheless
    1.17
     nevertheless
    1.08
     still
    0.84
     enough
    0.80
     certainly
    0.76
     sufficient
    0.75
     definitely
    0.72
     hey
    0.71
     better
    0.67
     adequate
    0.64
    Activations Density 0.242%

    No Known Activations