© 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. 4254
    Prev
    Next
    INDEX
    Explanations

    information related to inspections and technical details

    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
    394
    +0.34
    1.3%
    1842
    +0.34
    1.3%
    1177
    +0.19
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.34
    0.18
    394
    +0.34
    0.17
    324
    +0.19
    0.05
    Negative Logits
    <bos>
    -1.09
     Chwiliwch
    -0.59
     invokingState
    -0.55
    SharedDtor
    -0.54
    SneakyThrows
    -0.52
     ***!
    -0.50
     newOwner
    -0.49
    @[+][
    -0.48
    ьаж
    -0.48
     HttpNotFound
    -0.47
    POSITIVE LOGITS
     aen
    0.89
     emphat
    0.88
     Juf
    0.84
     maneu
    0.80
     thut
    0.80
     maer
    0.80
     sovere
    0.79
     Sarm
    0.79
     reft
    0.78
     feen
    0.77
    Activations Density 4.146%

    No Known Activations