© 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. 6709
    Prev
    Next
    INDEX
    Explanations

    information related to the Cyrillic alphabet and its historical significance

    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
    1150
    +0.15
    0.4%
    1819
    +0.13
    0.4%
    2034
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1819
    +0.15
    0.08
    1150
    +0.13
    0.02
    297
    +0.11
    0.05
    Negative Logits
     „,
    -0.91
     :)))
    -0.88
     eam
    -0.86
     ridu
    -0.85
     volu
    -0.85
     nece
    -0.84
     Febru
    -0.82
     ivi
    -0.82
     socie
    -0.82
     §.
    -0.82
    POSITIVE LOGITS
     instead
    1.01
    instead
    0.89
     Instead
    0.75
    Instead
    0.73
     rather
    0.71
     exclusively
    0.67
     вместо
    0.66
     predominance
    0.61
     cowards
    0.60
    rather
    0.59
    Activations Density 0.558%

    No Known Activations