© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7746
    Prev
    Next
    INDEX
    Explanations

    terms related to trauma, mental health conditions, emergency responders, and community support

    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
    50
    +0.31
    1.2%
    1577
    +0.22
    0.9%
    1013
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.31
    0.27
    1870
    +0.22
    0.13
    2044
    +0.13
    0.26
    Negative Logits
     succede
    -0.98
     trovo
    -0.94
     vorrei
    -0.88
    ⓧ
    -0.86
    ostante
    -0.83
     voleva
    -0.80
     torner
    -0.79
     affatto
    -0.78
     apparti
    -0.77
     sappiamo
    -0.77
    POSITIVE LOGITS
     impra
    0.90
     Operand
    0.89
     unspeak
    0.89
     Bartholo
    0.88
     inappro
    0.85
     indescri
    0.85
     Glou
    0.85
     Sarm
    0.84
     TokenType
    0.84
     Addr
    0.83
    Activations Density 7.341%

    No Known Activations