© 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. 13693
    Prev
    Next
    INDEX
    Explanations

    contact and address information

    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
    1343
    +0.18
    0.5%
    674
    +0.15
    0.4%
    24
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.18
    0.05
    1527
    +0.15
    0.03
    382
    +0.07
    0.03
    Negative Logits
     pamph
    -1.04
     inappro
    -0.92
     shenan
    -0.91
     unwarran
    -0.87
     Daven
    -0.82
     Illus
    -0.79
     impra
    -0.79
     racon
    -0.78
     unspeak
    -0.78
     Pamph
    -0.77
    POSITIVE LOGITS
     pama
    1.08
     kamb
    0.90
     bambu
    0.85
     siena
    0.84
     saul
    0.82
     susun
    0.78
    complished
    0.77
     gela
    0.77
     kuku
    0.76
     karte
    0.75
    Activations Density 0.137%

    No Known Activations