© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13835
    Prev
    Next
    INDEX
    Explanations

    text related to sci-fi and technological terms

    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
    2034
    +0.14
    0.4%
    184
    +0.10
    0.3%
    752
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1959
    +0.14
    0.06
    106
    +0.10
    0.04
    1445
    +0.10
    0.05
    Negative Logits
     ideolog
    -0.77
     reger
    -0.77
     guarn
    -0.69
     notor
    -0.69
     lapto
    -0.69
     patr
    -0.68
     €€
    -0.67
     controver
    -0.65
     acred
    -0.64
     sappi
    -0.64
    POSITIVE LOGITS
     Therefore
    0.59
    therefore
    0.57
     Fortunately
    0.56
     Thankfully
    0.56
    leyici
    0.56
     Luckily
    0.53
     This
    0.52
    idxs
    0.52
    Therefore
    0.51
     Hence
    0.51
    Activations Density 0.388%

    No Known Activations