© 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. 6300
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone's skills or abilities

    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
    605
    +0.13
    0.4%
    1974
    +0.10
    0.3%
    678
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    605
    +0.13
    0.02
    1974
    +0.10
    0.03
    1372
    +0.08
    0.03
    Negative Logits
     desir
    -1.68
     fta
    -1.60
     purcha
    -1.60
     increa
    -1.58
     aen
    -1.57
     fuf
    -1.56
     maneu
    -1.56
     strick
    -1.53
     inev
    -1.52
     waer
    -1.50
    POSITIVE LOGITS
     handling
    0.68
    Até
    0.59
    asteroide
    0.57
     handle
    0.56
    Muito
    0.55
     managing
    0.55
     못
    0.54
    astéro
    0.54
     skill
    0.54
     att
    0.54
    Activations Density 0.188%

    No Known Activations