© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5472
    Prev
    Next
    INDEX
    Explanations

    information or phrases related to statistical analysis and data

    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
    866
    +0.14
    0.5%
    31
    +0.13
    0.5%
    1520
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1520
    +0.14
    0.03
    31
    +0.13
    0.02
    1140
    +0.13
    0.03
    Negative Logits
     himo
    -0.68
    wieś
    -0.59
    gimento
    -0.56
     poveznice
    -0.52
     Ause
    -0.49
    └──
    -0.47
     indeb
    -0.47
    ፡
    -0.47
     Himo
    -0.47
     يتيمه
    -0.46
    POSITIVE LOGITS
     stat
    1.13
     statistics
    1.09
     STAT
    1.07
     Stat
    1.07
     stats
    1.04
     Statistic
    1.01
     statistic
    0.99
     Statistics
    0.98
     statistical
    0.98
    statistics
    0.98
    Activations Density 0.081%

    No Known Activations