© 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. 11087
    Prev
    Next
    INDEX
    Explanations

    quotations spoken by different individuals

    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
    1150
    +0.13
    0.4%
    1445
    +0.12
    0.4%
    453
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1373
    +0.13
    0.01
    1445
    +0.12
    0.04
    32
    +0.11
    0.03
    Negative Logits
    olphins
    -0.60
    crimination
    -0.58
     económicos
    -0.58
     frescas
    -0.57
    PLICIT
    -0.56
    =('
    -0.55
     OUTCOMES
    -0.55
     fresca
    -0.55
    PRESSION
    -0.55
     imagenes
    -0.55
    POSITIVE LOGITS
     Cfr
    1.36
     accla
    1.30
     Ibidem
    1.21
     Souha
    1.19
     ladite
    1.15
     Chapitre
    1.13
     reluct
    1.13
     depic
    1.13
     Molto
    1.10
     Augu
    1.09
    Activations Density 0.094%

    No Known Activations