© 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. 935
    Prev
    Next
    INDEX
    Explanations

    references to sports teams, players, and achievements

    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
    1978
    +0.12
    0.3%
    1253
    +0.10
    0.3%
    283
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1614
    +0.12
    0.06
    573
    +0.10
    0.05
    219
    +0.09
    0.04
    Negative Logits
     antimony
    -0.68
     turnips
    -0.64
     anhydrous
    -0.61
     rodziny
    -0.58
     electrolytic
    -0.58
     phosphoric
    -0.57
     bismuth
    -0.57
     anhyd
    -0.57
     desorption
    -0.56
     conifers
    -0.56
    POSITIVE LOGITS
     simplif
    1.36
     kosme
    1.25
     incess
    1.24
     exé
    1.22
     serai
    1.22
     praktik
    1.20
     soigne
    1.19
     kollek
    1.17
     minimalis
    1.15
     prouve
    1.14
    Activations Density 0.140%

    No Known Activations