© 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. 11594
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific reality show with detailed information about participants and their accomplishments

    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
    429
    +0.09
    0.3%
    2010
    +0.09
    0.3%
    643
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.09
    0.04
    643
    +0.09
    0.04
    1136
    +0.08
    0.04
    Negative Logits
     Solubility
    -0.67
     linseed
    -0.67
     phosphates
    -0.63
     phosphoric
    -0.62
     salic
    -0.59
     PHOSPH
    -0.58
     sentito
    -0.57
     dovr
    -0.57
     Ammonium
    -0.57
     flocc
    -0.56
    POSITIVE LOGITS
     contestants
    0.79
     contestant
    0.72
     radikal
    0.67
     praktik
    0.66
     akade
    0.64
     kompati
    0.63
     menyen
    0.62
     konserv
    0.61
     alkoh
    0.61
     vokal
    0.60
    Activations Density 0.378%

    No Known Activations