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. 1560
    Prev
    Next
    INDEX
    Explanations

    information related to academic papers and research studies

    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
    1034
    +0.13
    0.5%
    553
    +0.13
    0.5%
    789
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    789
    +0.13
    0.03
    553
    +0.13
    0.03
    1124
    +0.12
    0.03
    Negative Logits
    躇
    -0.59
    ARROLL
    -0.49
     breasted
    -0.49
    cciale
    -0.49
    المراجع
    -0.46
    vább
    -0.45
    erenc
    -0.42
    المصادر
    -0.42
    arrol
    -0.41
     Sprecher
    -0.41
    POSITIVE LOGITS
     paper
    1.41
    paper
    1.34
     Paper
    1.27
    Paper
    1.27
     papers
    1.22
     PAPER
    1.21
    papers
    1.07
    PAPER
    1.06
     Papers
    1.04
    Papers
    1.03
    Activations Density 0.066%

    No Known Activations