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. 10031
    Prev
    Next
    INDEX
    Explanations

    references to technical documentation and instructions

    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
    +0.15
    0.5%
    31
    +0.13
    0.4%
    1828
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1828
    +0.15
    0.10
    31
    +0.13
    0.07
    2011
    +0.13
    0.07
    Negative Logits
    }[!
    -0.74
     PicClick
    -0.72
    ViewFeatures
    -0.69
     biografias
    -0.67
    NameInMap
    -0.65
    Personendaten
    -0.65
    Lähteet
    -0.63
    PerformLayout
    -0.62
     Forumite
    -0.60
    CppMethod
    -0.60
    POSITIVE LOGITS
     indestru
    1.15
     récomp
    1.07
     shenan
    1.06
     snoopy
    1.05
     vété
    1.05
     maneu
    1.05
     délib
    1.03
     scrat
    1.03
     récon
    1.03
     confé
    1.02
    Activations Density 0.328%

    No Known Activations