© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3643
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing a foundation or basis for something

    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
    528
    +0.19
    0.7%
    1705
    +0.13
    0.5%
    1306
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    528
    +0.19
    0.03
    1705
    +0.13
    0.03
    1306
    +0.13
    0.03
    Negative Logits
     antik
    -0.46
     mals
    -0.46
    rvore
    -0.45
     gie
    -0.45
    Mä
    -0.45
     Mack
    -0.44
     intellig
    -0.43
     Mü
    -0.42
    Yh
    -0.41
    Menge
    -0.41
    POSITIVE LOGITS
     basis
    1.23
    basis
    1.21
     Basis
    1.17
    Basis
    1.10
     Bases
    0.94
     BASIS
    0.93
     bases
    0.89
    bases
    0.84
     getBase
    0.82
    Bases
    0.81
    Activations Density 0.064%

    No Known Activations