© 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. 6596
    Prev
    Next
    INDEX
    Explanations

    locations related to the North

    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
    897
    +0.18
    0.7%
    1376
    +0.16
    0.6%
    101
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.18
    0.04
    1376
    +0.16
    0.04
    897
    +0.14
    0.04
    Negative Logits
    сутствие
    -0.48
     mogę
    -0.48
     "..\..\
    -0.47
     musíte
    -0.46
     Турции
    -0.45
     má
    -0.45
     sanguí
    -0.44
    ньої
    -0.44
    нился
    -0.44
    dominal
    -0.43
    POSITIVE LOGITS
    North
    1.17
     Darío
    1.16
     North
    1.16
     NORTH
    1.09
     Marín
    1.07
     Áng
    1.02
     Román
    1.01
     canel
    1.01
     Nort
    1.01
     Noth
    1.00
    Activations Density 0.081%

    No Known Activations