© 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. 13902
    Prev
    Next
    INDEX
    Explanations

    locations and events related to migration and historical conflicts

    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
    1013
    +0.18
    0.6%
    227
    +0.17
    0.6%
    964
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    964
    +0.18
    0.07
    227
    +0.17
    0.08
    1499
    +0.17
    0.06
    Negative Logits
    <bos>
    -0.70
     sentire
    -0.65
     conosce
    -0.62
     esser
    -0.61
     imparare
    -0.61
     affez
    -0.61
    nă
    -0.59
     riesce
    -0.58
     intercooler
    -0.58
     succede
    -0.58
    POSITIVE LOGITS
     ftu
    1.41
     fta
    1.32
     fays
    1.31
     vns
    1.29
     fup
    1.29
     ftre
    1.27
     »>
    1.21
     reft
    1.20
     fto
    1.20
     fign
    1.20
    Activations Density 0.265%

    No Known Activations