© 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. 2239
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and events

    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
    1978
    +0.18
    0.6%
    499
    +0.12
    0.4%
    1870
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.18
    0.09
    1614
    +0.12
    0.09
    573
    +0.12
    0.07
    Negative Logits
    lieferung
    -0.54
     allegorical
    -0.52
     сте
    -0.51
    .
    -0.50
     little
    -0.50
    ↵↵
    -0.49
    füllung
    -0.48
    滑动
    -0.47
     أ
    -0.47
     a
    -0.47
    POSITIVE LOGITS
     alkoh
    1.40
     kosme
    1.39
     utop
    1.33
     plak
    1.30
     makro
    1.29
     kollek
    1.29
     silikon
    1.28
     kram
    1.25
     hek
    1.25
     elek
    1.25
    Activations Density 0.176%

    No Known Activations