© 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. 1075
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, particularly Nigeria, and possibly surrounding context

    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
    50
    +0.27
    1.1%
    1842
    +0.20
    0.8%
    609
    +0.18
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.27
    0.05
    227
    +0.20
    0.04
    964
    +0.18
    0.02
    Negative Logits
    ďaka
    -0.49
     defaultstate
    -0.48
    geslacht
    -0.45
     Winaray
    -0.44
     kuhusu
    -0.44
    戎
    -0.43
     længere
    -0.42
     iNdEx
    -0.42
    IVEREF
    -0.42
     pinulongan
    -0.42
    POSITIVE LOGITS
     pymysql
    0.80
    «<
    0.71
     accla
    0.69
     reluct
    0.68
     ftu
    0.68
     cartier
    0.67
     emphat
    0.66
     maneu
    0.66
     shenan
    0.66
     fta
    0.66
    Activations Density 0.242%

    No Known Activations