© 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. 7772
    Prev
    Next
    INDEX
    Explanations

    details related to programs, medical situations, or team interactions, such as hospital programs, team activities, and medical trials

    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
    1870
    +0.17
    0.5%
    1385
    +0.13
    0.4%
    1438
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.17
    0.04
    379
    +0.13
    0.03
    264
    +0.09
    0.03
    Negative Logits
     disreg
    -1.27
     snoopy
    -1.13
     depic
    -1.13
     véritables
    -1.12
     peppa
    -1.08
     cushi
    -1.08
     scrat
    -1.06
     unve
    -1.05
     increa
    -1.05
     impra
    -1.05
    POSITIVE LOGITS
     keramik
    0.90
     alkoh
    0.79
     fono
    0.77
     ideolog
    0.77
     poros
    0.77
     praktik
    0.76
     meras
    0.74
    bulos
    0.73
     alfabe
    0.72
     foton
    0.72
    Activations Density 0.356%

    No Known Activations