© 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. 11618
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent or unfortunate incidents

    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
    +0.24
    0.7%
    1967
    +0.16
    0.5%
    674
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.24
    0.07
    1166
    +0.16
    0.08
    1842
    +0.14
    0.06
    Negative Logits
     michelin
    -1.23
     cabrio
    -1.21
     impra
    -1.07
     reluct
    -1.04
     effe
    -1.03
     shenan
    -1.02
     cushi
    -1.02
     Realt
    -1.01
     maneu
    -1.01
     indestru
    -1.01
    POSITIVE LOGITS
    <bos>
    0.91
    __":
    0.68
     تضيفلها
    0.65
    Referencies
    0.53
    leyebilirsiniz
    0.52
    Välislingid
    0.52
    +:+
    0.52
    leyball
    0.51
    Visión
    0.51
    ɵɵelementEnd
    0.50
    Activations Density 0.729%

    No Known Activations