© 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 EvalsExportsinterp-engineNEWAPI 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. 16331
    Prev
    Next
    INDEX
    Explanations

    references to supernatural or paranormal activities

    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
    906
    +0.20
    0.6%
    736
    +0.11
    0.4%
    856
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.20
    0.07
    906
    +0.11
    0.01
    184
    +0.11
    0.02
    Negative Logits
     embra
    -2.00
     hcm
    -1.98
     „,
    -1.95
     gmbh
    -1.93
     lele
    -1.93
     wien
    -1.92
     optik
    -1.92
     emphat
    -1.90
     fuf
    -1.90
     bayern
    -1.89
    POSITIVE LOGITS
     seemed
    0.87
     seem
    0.80
     seems
    0.72
     jakby
    0.69
     looked
    0.67
     felé
    0.67
     something
    0.64
    <bos>
    0.64
    似乎
    0.63
     org
    0.62
    Activations Density 0.336%

    No Known Activations