© 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. 7683
    Prev
    Next
    INDEX
    Explanations

    scientific and political terms related to government, research, and social issues

    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
    1842
    +0.12
    0.4%
    752
    +0.12
    0.4%
    856
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.12
    0.05
    16
    +0.12
    0.07
    939
    +0.12
    0.06
    Negative Logits
     disreg
    -0.95
     cryst
    -0.81
     suscep
    -0.79
     swarovski
    -0.78
     unden
    -0.76
     ftw
    -0.76
     intermitt
    -0.75
     scrat
    -0.74
     snoopy
    -0.74
     cushi
    -0.73
    POSITIVE LOGITS
    iglesia
    0.65
     PLWABN
    0.64
     Tangerang
    0.63
     Bekasi
    0.63
     Lampung
    0.60
    IntoConstraints
    0.60
     Asunción
    0.58
     elections
    0.57
     Makassar
    0.57
    Skocz
    0.56
    Activations Density 0.504%

    No Known Activations