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

    Neuronpedia

    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. 7484
    Prev
    Next
    INDEX
    Explanations

    statements related to advantages or benefits

    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
    2030
    +0.11
    0.3%
    1539
    +0.09
    0.3%
    1601
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2030
    +0.11
    0.05
    1519
    +0.09
    0.05
    124
    +0.08
    0.03
    Negative Logits
     pessi
    -1.22
     igno
    -1.21
     accla
    -1.19
     emphat
    -1.18
     embra
    -1.16
     fte
    -1.15
     nutr
    -1.15
     oner
    -1.13
     fuf
    -1.13
     inev
    -1.13
    POSITIVE LOGITS
    fromLTRB
    0.65
     of
    0.64
    agisse
    0.61
    agissait
    0.60
    PhysRevD
    0.56
    Ventajas
    0.56
    thinkable
    0.53
    cheidung
    0.53
     februar
    0.53
     že
    0.53
    Activations Density 0.228%

    No Known Activations