© 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. 10859
    Prev
    Next
    INDEX
    Explanations

    sentences related to personal empowerment and counter-cultural defiance

    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
    991
    +0.08
    0.2%
    247
    +0.08
    0.2%
    882
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.08
    0.04
    1579
    +0.08
    0.04
    991
    +0.08
    0.03
    Negative Logits
     emphat
    -0.61
     geograf
    -0.60
     Aktiv
    -0.60
     ?...
    -0.59
     minimalis
    -0.59
     pessi
    -0.59
     deff
    -0.58
     favori
    -0.58
     laun
    -0.57
     dynamis
    -0.56
    POSITIVE LOGITS
     anymore
    0.71
     whether
    0.57
     WHETHER
    0.55
     barbacoa
    0.54
    ázaro
    0.53
     zirc
    0.53
     nutella
    0.53
     silty
    0.53
     if
    0.52
     bemerken
    0.52
    Activations Density 0.205%

    No Known Activations