© 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. 14081
    Prev
    Next
    INDEX
    Explanations

    references to specific US states, particularly Nebraska and Lincoln

    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
    390
    +0.16
    0.7%
    101
    +0.14
    0.6%
    874
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.16
    0.04
    1177
    +0.14
    0.02
    390
    +0.13
    0.03
    Negative Logits
     aislada
    -0.49
     gøre
    -0.48
     bună
    -0.48
    Pued
    -0.46
    kusen
    -0.45
     saada
    -0.44
     fiquei
    -0.44
     parecia
    -0.44
    melada
    -0.44
     trouxe
    -0.44
    POSITIVE LOGITS
     Nebraska
    1.23
    Nebraska
    1.16
     Lincoln
    1.13
    Lincoln
    1.11
     LINCOLN
    1.08
     Omaha
    1.01
     lincoln
    0.96
     Neb
    0.95
    Omaha
    0.88
    Neb
    0.87
    Activations Density 0.232%

    No Known Activations