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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 925
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental, scientific, and regulatory topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.18
    0.6%
    1343
    +0.10
    0.4%
    856
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.18
    0.06
    809
    +0.10
    0.05
    1870
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.43
    SequentialGroup
    -0.76
     AssemblyVersion
    -0.69
     vielmehr
    -0.64
    Pozri
    -0.59
     snippetHide
    -0.59
     Betracht
    -0.57
    setDo
    -0.56
     freilich
    -0.56
    SourceChecksum
    -0.55
    POSITIVE LOGITS
     silikon
    1.62
     plak
    1.60
     karton
    1.54
     lele
    1.52
     keramik
    1.47
     optik
    1.45
     logis
    1.45
     makro
    1.45
     elek
    1.44
     alkoh
    1.43
    Activations Density 0.338%

    No Known Activations