© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11954
    Prev
    Next
    INDEX
    Explanations

    references to a character named Valeri or Val

    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
    1271
    +0.15
    0.7%
    481
    +0.13
    0.6%
    390
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.15
    0.03
    1271
    +0.13
    0.03
    239
    +0.12
    0.02
    Negative Logits
     dovrebbero
    -0.52
     ngayon
    -0.51
     kapag
    -0.47
     itong
    -0.47
     cominci
    -0.47
     persino
    -0.47
     Tuc
    -0.47
     bago
    -0.46
     siyang
    -0.45
     cammin
    -0.45
    POSITIVE LOGITS
     VAL
    1.22
     Val
    1.13
     val
    1.12
    Val
    1.03
    val
    0.98
    VAL
    0.97
     Valley
    0.96
    Valley
    0.95
     valley
    0.93
     vale
    0.91
    Activations Density 0.098%

    No Known Activations