© 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. 7745
    Prev
    Next
    INDEX
    Explanations

    technical specifications and functionalities related to electronic devices

    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
    876
    +0.12
    0.4%
    381
    +0.10
    0.3%
    690
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.12
    0.04
    1446
    +0.10
    0.03
    724
    +0.10
    0.03
    Negative Logits
     Bibl
    -1.07
     gubern
    -0.99
     Muhamma
    -0.98
     maksi
    -0.93
     panik
    -0.92
     Strukt
    -0.92
     Lampung
    -0.88
     Banten
    -0.86
     Annales
    -0.85
     Khart
    -0.85
    POSITIVE LOGITS
     bandeau
    0.80
     ecru
    0.77
     tricot
    0.76
     BEAUT
    0.74
     beeind
    0.72
     😍😍
    0.72
     garçons
    0.72
    reszcie
    0.71
     amigurumi
    0.71
     merve
    0.70
    Activations Density 0.188%

    No Known Activations