© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7730
    Prev
    Next
    INDEX
    Explanations

    medical procedures and improvements in health conditions

    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
    +0.09
    0.3%
    311
    +0.08
    0.2%
    964
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.09
    0.05
    311
    +0.08
    0.02
    288
    +0.08
    0.03
    Negative Logits
     encomp
    -1.56
     Intere
    -1.49
     reluct
    -1.48
     disagre
    -1.47
     increa
    -1.47
     accla
    -1.46
     embra
    -1.44
     depic
    -1.44
     Simult
    -1.44
     impra
    -1.44
    POSITIVE LOGITS
    <bos>
    0.76
     дописавши
    0.66
     walking
    0.60
    Демографія
    0.58
    IsMutable
    0.58
     walk
    0.58
     normal
    0.57
    ModelAdmin
    0.57
     daily
    0.57
     forState
    0.56
    Activations Density 0.368%

    No Known Activations