© 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. 6012
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'inject' or related terms

    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
    920
    +0.13
    0.5%
    860
    +0.12
    0.4%
    1763
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    860
    +0.13
    0.02
    316
    +0.12
    0.02
    1763
    +0.12
    0.02
    Negative Logits
     Fim
    -0.52
     Compre
    -0.52
     Valerio
    -0.50
     Vou
    -0.49
    Gren
    -0.47
     auster
    -0.47
     Utili
    -0.46
     Tela
    -0.45
     Apre
    -0.45
     Perd
    -0.44
    POSITIVE LOGITS
     inject
    1.16
     injection
    1.15
     injected
    1.06
     injecting
    1.05
     injections
    1.03
     Injection
    1.00
    injection
    0.99
    inject
    0.95
    Inject
    0.91
     Inject
    0.91
    Activations Density 0.099%

    No Known Activations