© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 11925
    Prev
    Next
    INDEX
    Explanations

    the word "option" along with discussions or examples of different options

    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
    420
    +0.13
    0.5%
    1265
    +0.13
    0.5%
    47
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.13
    0.03
    420
    +0.13
    0.04
    47
    +0.12
    0.03
    Negative Logits
     tamen
    -0.76
     ejus
    -0.73
     nutella
    -0.73
     quæ
    -0.71
     sambal
    -0.68
     jorge
    -0.68
     mascarpone
    -0.68
     habet
    -0.65
     barbacoa
    -0.65
     haer
    -0.64
    POSITIVE LOGITS
     option
    1.44
     options
    1.34
     Option
    1.34
    option
    1.33
     Options
    1.27
    Option
    1.27
     OPTION
    1.20
    options
    1.19
    OPTION
    1.14
    Options
    1.12
    Activations Density 0.063%

    No Known Activations