© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4073
    Prev
    Next
    INDEX
    Explanations

    text related to instructions, specifically in the context of assembly steps and guidance

    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
    1108
    +0.13
    0.4%
    569
    +0.11
    0.3%
    1244
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    569
    +0.13
    0.08
    1244
    +0.11
    0.04
    1108
    +0.11
    0.07
    Negative Logits
    toBe
    -0.60
    DisplayMetrics
    -0.50
    tembro
    -0.49
    Prova
    -0.49
    TypedValue
    -0.47
    Carreira
    -0.47
     clicar
    -0.46
    ╬
    -0.46
    !("{
    -0.46
    Bild
    -0.46
    POSITIVE LOGITS
     hairc
    1.36
     embodi
    1.17
     milf
    1.15
     scrat
    1.09
     swarovski
    1.09
     impra
    1.05
     maneu
    1.04
     gaily
    0.99
     xenia
    0.98
     inext
    0.98
    Activations Density 0.553%

    No Known Activations