© 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. 6379
    Prev
    Next
    INDEX
    Explanations

    phrases related to observation, examination, or analysis

    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
    872
    +0.11
    0.3%
    113
    +0.09
    0.3%
    1264
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.11
    0.03
    1039
    +0.09
    0.03
    2027
    +0.08
    0.02
    Negative Logits
     colesterol
    -0.51
     виправивши
    -0.47
    Jäh
    -0.43
    Semitism
    -0.43
     verze
    -0.42
    amsmath
    -0.41
    amssymb
    -0.41
     Eliminar
    -0.41
    uche
    -0.40
     HasFactory
    -0.40
    POSITIVE LOGITS
     aen
    1.00
     waer
    0.95
     apprehen
    0.93
     hairc
    0.91
     gild
    0.91
     scrat
    0.89
     minnie
    0.89
     meis
    0.88
     ftu
    0.87
     tew
    0.87
    Activations Density 0.232%

    No Known Activations