© 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. 12975
    Prev
    Next
    INDEX
    Explanations

    organizations, collaborative efforts, countries, and significant historical events

    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
    198
    +0.15
    0.4%
    227
    +0.13
    0.4%
    605
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.15
    0.06
    1252
    +0.13
    0.04
    1824
    +0.11
    0.03
    Negative Logits
    setDo
    -0.67
    AIRS
    -0.62
    IVERSITY
    -0.61
    YNAMICS
    -0.60
    ATEGY
    -0.59
    IUrlHelper
    -0.58
    FORCEMENT
    -0.58
    fjspx
    -0.58
     chilena
    -0.58
     OUTCOMES
    -0.58
    POSITIVE LOGITS
     accla
    1.38
     secon
    1.25
     emphat
    1.25
     unden
    1.25
     squa
    1.24
     increa
    1.23
     inev
    1.22
     fta
    1.20
     embra
    1.19
     inext
    1.18
    Activations Density 0.287%

    No Known Activations