© 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. 6166
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology features and developments

    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
    1042
    +0.14
    0.4%
    382
    +0.14
    0.4%
    2034
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.14
    0.08
    1265
    +0.14
    0.07
    257
    +0.13
    0.05
    Negative Logits
     mef
    -1.80
     effe
    -1.68
     fta
    -1.68
     sii
    -1.61
     erec
    -1.60
     fte
    -1.59
     emphat
    -1.59
     nece
    -1.56
     maroc
    -1.55
     embra
    -1.55
    POSITIVE LOGITS
     nor
    1.38
    nor
    1.02
     unless
    1.00
     except
    0.98
     sondern
    0.95
     but
    0.94
     yet
    0.89
     although
    0.88
     despite
    0.87
    except
    0.86
    Activations Density 0.300%

    No Known Activations