© 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. 5369
    Prev
    Next
    INDEX
    Explanations

    information related to technical systems or operations

    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
    1967
    +0.19
    0.6%
    2019
    +0.13
    0.4%
    776
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.19
    0.04
    501
    +0.13
    0.03
    1967
    +0.11
    0.03
    Negative Logits
     affez
    -0.86
     abbra
    -0.81
     allarg
    -0.77
     vogli
    -0.74
     découver
    -0.72
     €/
    -0.71
     venuto
    -0.70
     fatis
    -0.70
     vne
    -0.67
    IUrlHelper
    -0.67
    POSITIVE LOGITS
     unspeak
    0.79
     indescri
    0.70
    )}
    0.63
    })$
    0.59
     unavoid
    0.58
    ,)
    0.58
     exasper
    0.58
    |)
    0.57
    >)
    0.57
     intrigu
    0.57
    Activations Density 0.164%

    No Known Activations