© 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. 3548
    Prev
    Next
    INDEX
    Explanations

    patterns related to numerical sequences or codes

    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
    16
    +0.19
    0.6%
    1741
    +0.15
    0.5%
    1343
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    895
    +0.19
    0.03
    382
    +0.15
    0.04
    499
    +0.11
    0.03
    Negative Logits
     asado
    -0.85
     sement
    -0.85
     lemp
    -0.82
    CRETE
    -0.80
    thical
    -0.80
     rossi
    -0.79
     berge
    -0.78
     feo
    -0.76
     rosado
    -0.75
     crudo
    -0.73
    POSITIVE LOGITS
     clô
    1.32
     bénéfice
    1.28
     montrant
    1.27
     télécharge
    1.25
     recrutement
    1.25
     règlement
    1.24
     complément
    1.21
     appuy
    1.20
     Jusqu
    1.20
     mécanisme
    1.20
    Activations Density 0.115%

    No Known Activations