© 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 EvalsExportsinterp-engineNEWAPI 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. 4722
    Prev
    Next
    INDEX
    Explanations

    descriptions of disturbing or violent imagery

    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
    1842
    +0.23
    0.7%
    1177
    +0.18
    0.6%
    906
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.23
    0.07
    1842
    +0.18
    0.09
    1778
    +0.13
    0.06
    Negative Logits
    xiang
    -0.52
     substantially
    -0.47
    LookAnd
    -0.47
     significantly
    -0.46
    Hướng
    -0.44
     ​​
    -0.44
    Rub
    -0.44
     obvio
    -0.44
     attributable
    -0.43
    assertj
    -0.43
    POSITIVE LOGITS
     fluo
    1.42
     beft
    1.27
     fign
    1.26
     ftu
    1.24
     ftre
    1.22
     cytoplas
    1.19
     reafon
    1.19
     swarovski
    1.18
     noss
    1.17
     reft
    1.17
    Activations Density 2.025%

    No Known Activations