© 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. 911
    Prev
    Next
    INDEX
    Explanations

    references to Mars and space missions

    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
    1472
    +0.16
    0.6%
    1983
    +0.15
    0.6%
    421
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1472
    +0.16
    0.03
    1983
    +0.15
    0.02
    421
    +0.12
    0.02
    Negative Logits
    UnusedPrivate
    -0.60
     esternos
    -0.58
    StoreMessageInfo
    -0.57
    NSYLVANIA
    -0.52
    sizeCache
    -0.52
    oa̍t
    -0.51
    ésultat
    -0.51
    richTextPanel
    -0.51
     beren
    -0.50
     liel
    -0.49
    POSITIVE LOGITS
     Mars
    1.34
    Mars
    1.30
     MARS
    1.16
     disagre
    1.09
     impra
    1.08
     mars
    1.06
     hairc
    1.05
     scrat
    1.04
     inext
    1.04
     excru
    1.03
    Activations Density 0.064%

    No Known Activations