© 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. 4440
    Prev
    Next
    INDEX
    Explanations

    references to physical actions or processes

    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
    1013
    +0.16
    0.5%
    1842
    +0.11
    0.3%
    1654
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.16
    0.08
    284
    +0.11
    0.07
    1842
    +0.10
    0.06
    Negative Logits
     Ottobre
    -1.28
     Settembre
    -1.20
     parteci
    -1.17
     Luglio
    -1.15
     sappi
    -1.14
     poichè
    -1.13
     affez
    -1.12
     gius
    -1.11
     Giugno
    -1.09
     ?...
    -1.08
    POSITIVE LOGITS
     while
    1.01
    while
    0.84
     whilst
    0.82
     until
    0.81
     during
    0.72
    .
    0.69
    While
    0.69
     alongside
    0.68
     While
    0.68
     till
    0.67
    Activations Density 0.623%

    No Known Activations