© 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. 4033
    Prev
    Next
    INDEX
    Explanations

    websites or URLs containing specific words or phrases

    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
    1705
    +0.11
    0.3%
    50
    +0.11
    0.3%
    1967
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.11
    0.13
    1705
    +0.11
    0.11
    394
    +0.10
    0.09
    Negative Logits
     tranquillo
    -0.76
     incess
    -0.74
     boxe
    -0.73
     vivace
    -0.72
     violon
    -0.72
     aquare
    -0.71
     batte
    -0.71
     apparti
    -0.71
     divertimento
    -0.70
     chèvre
    -0.70
    POSITIVE LOGITS
    Hk
    0.57
    Vv
    0.54
    Xb
    0.53
    Gz
    0.50
    Xf
    0.50
    Xr
    0.50
    Rz
    0.50
    Yg
    0.49
     fondée
    0.49
    fP
    0.49
    Activations Density 1.617%

    No Known Activations