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. 582
    Prev
    Next
    INDEX
    Explanations

    numerical figures that represent measurements or quantities

    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
    1978
    +0.18
    0.6%
    776
    +0.17
    0.5%
    1535
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.18
    0.08
    1978
    +0.17
    0.06
    382
    +0.16
    0.05
    Negative Logits
    <bos>
    -0.65
     motherfucker
    -0.65
     vergeten
    -0.64
    landschaft
    -0.64
     zupełnie
    -0.60
     maniac
    -0.60
     święta
    -0.60
     voelen
    -0.60
     przekon
    -0.59
     chcą
    -0.59
    POSITIVE LOGITS
     utop
    1.66
     alkoh
    1.64
     silikon
    1.59
     solidar
    1.53
     kosme
    1.52
     minimalis
    1.50
     mikrofon
    1.50
     antik
    1.49
     kön
    1.48
     keramik
    1.47
    Activations Density 0.257%

    No Known Activations