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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3497
    Prev
    Next
    INDEX
    Explanations

    detailed information about healthcare policy and financial reimbursement mechanisms

    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
    +0.13
    0.4%
    1253
    +0.10
    0.3%
    1385
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.13
    0.04
    216
    +0.10
    0.03
    1547
    +0.08
    0.03
    Negative Logits
    ciless
    -0.51
    loroethene
    -0.50
    isContained
    -0.48
    plier
    -0.46
    irmish
    -0.45
    omini
    -0.44
    IActionResult
    -0.44
    ceis
    -0.43
    ourge
    -0.42
     TextAlign
    -0.42
    POSITIVE LOGITS
     nicolas
    0.69
     javier
    0.68
     isuzu
    0.67
     panasonic
    0.67
     piaggio
    0.66
     roberto
    0.66
     lamborghini
    0.66
     tranf
    0.65
     peugeot
    0.65
     alberto
    0.64
    Activations Density 0.246%

    No Known Activations