© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 900
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions and events

    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
    604
    +0.22
    0.7%
    184
    +0.21
    0.6%
    1150
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.22
    0.01
    1804
    +0.21
    0.03
    1430
    +0.12
    0.02
    Negative Logits
     increa
    -1.38
     disagre
    -1.36
     reluct
    -1.32
     tricot
    -1.28
     hcm
    -1.26
     impra
    -1.26
     accla
    -1.26
     greate
    -1.23
     embodi
    -1.23
     affor
    -1.22
    POSITIVE LOGITS
    FailureListener
    0.73
    IsContent
    0.66
     seemed
    0.66
    ContentAlignment
    0.65
     kiệm
    0.61
     noiembrie
    0.61
    República
    0.60
    Economía
    0.60
    (":");
    0.60
     бър
    0.60
    Activations Density 0.167%

    No Known Activations