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. 3067
    Prev
    Next
    INDEX
    Explanations

    questions related to challenges or problems that individuals or communities face

    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
    630
    +0.14
    0.4%
    1038
    +0.08
    0.2%
    990
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    630
    +0.14
    0.05
    990
    +0.08
    0.03
    411
    +0.08
    0.03
    Negative Logits
    Personendaten
    -0.56
    ">...
    -0.55
     resultMap
    -0.51
    ">.
    -0.50
     lancia
    -0.48
    ofür
    -0.45
    OGND
    -0.45
     esquecer
    -0.45
     viera
    -0.44
    ">+
    -0.43
    POSITIVE LOGITS
     challenges
    0.91
     challenge
    0.83
     hurdles
    0.80
    challenges
    0.79
     Challenges
    0.78
    Challenges
    0.76
     hurdle
    0.74
     obstacles
    0.72
     obstacle
    0.70
     Obstacle
    0.68
    Activations Density 0.328%

    No Known Activations