© 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. 12782
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to historical 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
    168
    +0.15
    0.6%
    489
    +0.14
    0.6%
    1265
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.15
    0.05
    168
    +0.14
    0.04
    950
    +0.14
    0.04
    Negative Logits
    akukan
    -0.52
     CascadeType
    -0.48
    ønne
    -0.48
    ghijklmnop
    -0.47
    diğimiz
    -0.46
    IZABETH
    -0.44
     ویکی‌پدیای
    -0.44
    ıca
    -0.44
     maxn
    -0.43
    cektir
    -0.43
    POSITIVE LOGITS
    Gil
    0.85
     GIL
    0.82
    gil
    0.81
     Gil
    0.80
    GIL
    0.78
    Cil
    0.78
    il
    0.74
     Pil
    0.72
     gil
    0.71
     Cil
    0.71
    Activations Density 0.244%

    No Known Activations