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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1966
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research, technical procedures, and intellectual concepts

    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
    1177
    +0.12
    0.3%
    678
    +0.11
    0.3%
    289
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.12
    0.06
    1608
    +0.11
    0.02
    468
    +0.09
    0.04
    Negative Logits
     *++
    -0.65
    XmlEnum
    -0.60
    Jeografia
    -0.57
     MessageBoxIcon
    -0.53
     تانيه
    -0.52
     coté
    -0.52
     autorytatywna
    -0.51
     esternos
    -0.50
    Jereo
    -0.49
    |<\
    -0.49
    POSITIVE LOGITS
     pensato
    0.73
     venuto
    0.71
     affez
    0.70
     voleva
    0.70
     sentito
    0.68
     palet
    0.68
     provato
    0.67
     chiesto
    0.65
     pama
    0.65
     riuscito
    0.65
    Activations Density 0.489%

    No Known Activations