© 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. 13245
    Prev
    Next
    INDEX
    Explanations

    mentions of social issues, government initiatives, and city development

    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
    764
    +0.16
    0.5%
    1870
    +0.12
    0.4%
    227
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.16
    0.07
    284
    +0.12
    0.08
    875
    +0.11
    0.04
    Negative Logits
     sappi
    -1.67
     affez
    -1.51
     dises
    -1.50
     ?...
    -1.47
     thut
    -1.42
     fep
    -1.41
     vogli
    -1.40
     parteci
    -1.39
     !...
    -1.38
     ftu
    -1.37
    POSITIVE LOGITS
     through
    0.90
     by
    0.81
     via
    0.81
     throughout
    0.75
     while
    0.74
     in
    0.72
     across
    0.71
     during
    0.70
     amid
    0.69
    .
    0.69
    Activations Density 0.851%

    No Known Activations