© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14621
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic locations

    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
    1331
    +0.17
    0.7%
    896
    +0.17
    0.7%
    1472
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1331
    +0.17
    0.04
    896
    +0.17
    0.02
    1895
    +0.14
    0.03
    Negative Logits
    thinkable
    -0.48
    topRight
    -0.43
     Küchen
    -0.43
    mistak
    -0.43
    AndroidJUnit
    -0.40
    Trichlor
    -0.39
     convulsions
    -0.39
    TouchEvent
    -0.39
    cún
    -0.39
    huriyet
    -0.38
    POSITIVE LOGITS
     Bal
    1.32
    Bal
    1.28
     bal
    1.21
    bal
    1.19
     BAL
    1.18
    BAL
    1.05
     Balo
    0.97
     Ballot
    0.91
     Balla
    0.88
     ftill
    0.87
    Activations Density 0.090%

    No Known Activations