© 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. 13419
    Prev
    Next
    INDEX
    Explanations

    words related to the exploitation of animals for various purposes

    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
    198
    +0.13
    0.4%
    1385
    +0.12
    0.4%
    1842
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    923
    +0.13
    0.03
    1857
    +0.12
    0.02
    1293
    +0.10
    0.04
    Negative Logits
     pamph
    -0.96
     quitted
    -0.86
     apprehen
    -0.81
     reconno
    -0.81
     Moslem
    -0.72
     gaily
    -0.72
     Minang
    -0.71
     marcato
    -0.71
     Shakspeare
    -0.71
     shenan
    -0.70
    POSITIVE LOGITS
     szóci
    0.52
    annica
    0.49
     \%$\\
    0.46
     parfum
    0.45
    used
    0.44
    askets
    0.44
     dishes
    0.43
     salads
    0.43
     FUNERAL
    0.43
     used
    0.42
    Activations Density 0.315%

    No Known Activations