© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11056
    Prev
    Next
    INDEX
    Explanations

    references to historical and geographical aspects related to Iceland

    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
    1961
    +0.13
    0.5%
    31
    +0.13
    0.4%
    545
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.13
    0.03
    732
    +0.13
    0.03
    314
    +0.13
    0.02
    Negative Logits
     Jä
    -0.63
     Nö
    -0.62
    Fär
    -0.61
    ComponentName
    -0.61
     Antik
    -0.61
     kram
    -0.61
    Hü
    -0.60
     krab
    -0.59
     Gä
    -0.59
     Fär
    -0.58
    POSITIVE LOGITS
     Icelandic
    1.13
     Iceland
    1.07
     disagre
    1.04
     unwarran
    1.03
    Iceland
    0.99
     unspeak
    0.98
     Mlle
    0.96
     impractica
    0.96
     inconce
    0.95
     volunte
    0.95
    Activations Density 0.158%

    No Known Activations