Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3044
    Prev
    Next
    INDEX
    Explanations

    mentions of books and publications

    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
    752
    +0.19
    0.6%
    16
    +0.19
    0.6%
    1177
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.19
    0.08
    752
    +0.19
    0.06
    764
    +0.13
    0.05
    Negative Logits
     semmi
    -0.93
    ertion
    -0.90
    idated
    -0.87
    riction
    -0.82
     rather
    -0.80
     inkább
    -0.79
     head
    -0.79
    Đây
    -0.78
     итоге
    -0.78
     들
    -0.78
    POSITIVE LOGITS
     confé
    2.23
     Chapitre
    2.09
     hcm
    2.02
     Sén
    2.02
     délib
    2.01
     Strukt
    1.97
     rafra
    1.96
     Cfr
    1.95
     vété
    1.93
     déliv
    1.93
    Activations Density 0.339%

    No Known Activations