© 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. 877
    Prev
    Next
    INDEX
    Explanations

    text related to advanced technology and modern applications

    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
    1870
    +0.14
    0.4%
    678
    +0.14
    0.4%
    50
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.14
    0.09
    651
    +0.14
    0.05
    1870
    +0.12
    0.05
    Negative Logits
    <bos>
    -1.31
    HideFlags
    -0.77
    wieś
    -0.76
    GEBURTSDATUM
    -0.73
     المعيارى
    -0.71
     typelib
    -0.70
    WireFormat
    -0.69
    पया
    -0.69
    rungsseite
    -0.69
     kasarigan
    -0.67
    POSITIVE LOGITS
     aen
    1.14
     Augu
    1.11
     hcm
    1.05
     Hn
    1.04
     Whence
    1.04
     Fasc
    1.03
     Minang
    1.03
     inev
    1.03
     Juf
    1.02
     Confu
    1.02
    Activations Density 0.816%

    No Known Activations