© 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. 13698
    Prev
    Next
    INDEX
    Explanations

    verbs related to programming and software development processes, such as creating, developing, and writing

    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
    678
    +0.14
    0.4%
    1984
    +0.14
    0.4%
    468
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.14
    0.08
    911
    +0.14
    0.04
    1531
    +0.10
    0.04
    Negative Logits
     désigne
    -0.67
     résulte
    -0.66
     contribue
    -0.64
     restera
    -0.64
     occupe
    -0.64
     ressemble
    -0.62
     devra
    -0.62
     apparaît
    -0.59
     accueille
    -0.59
     affirme
    -0.59
    POSITIVE LOGITS
     hairc
    0.96
     considér
    0.95
     délib
    0.89
     mahd
    0.85
     osal
    0.85
     semblables
    0.84
     pleins
    0.83
     écout
    0.83
     destinées
    0.83
     embodi
    0.81
    Activations Density 0.542%

    No Known Activations