© 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. 10995
    Prev
    Next
    INDEX
    Explanations

    descriptions related to locations and infrastructures

    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
    1577
    +0.19
    0.7%
    1013
    +0.15
    0.5%
    394
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.19
    0.14
    1056
    +0.15
    0.17
    2044
    +0.14
    0.24
    Negative Logits
     voleva
    -0.96
     firent
    -0.95
     affez
    -0.88
     récla
    -0.83
     Ottobre
    -0.80
     faisaient
    -0.79
     mourut
    -0.79
     faceva
    -0.77
     zumal
    -0.76
     Settembre
    -0.74
    POSITIVE LOGITS
     was
    0.68
     seemed
    0.67
     were
    0.66
     wasn
    0.66
     weren
    0.66
     lacked
    0.66
     consisted
    0.65
     didn
    0.63
     differed
    0.62
     wasnt
    0.61
    Activations Density 9.456%

    No Known Activations