© 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. 14742
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes and stories about family

    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
    964
    +0.11
    0.3%
    1842
    +0.10
    0.3%
    906
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.11
    0.07
    1533
    +0.10
    0.02
    343
    +0.09
    0.06
    Negative Logits
     umo
    -0.67
     Jä
    -0.65
     surpl
    -0.64
     Simult
    -0.64
     parall
    -0.59
     asos
    -0.57
     kasa
    -0.57
     Illus
    -0.56
     Gorb
    -0.55
     makro
    -0.55
    POSITIVE LOGITS
    <bos>
    0.70
     parents
    0.58
    preco
    0.56
     school
    0.53
     dad
    0.52
    parents
    0.52
     kids
    0.51
     kid
    0.50
     PeEnEo
    0.50
     Parents
    0.50
    Activations Density 0.636%

    No Known Activations