© 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. 922
    Prev
    Next
    INDEX
    Explanations

    places, objects, and descriptions related to a specific location or setting

    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
    1150
    +0.16
    0.5%
    478
    +0.14
    0.5%
    1842
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.16
    0.07
    1705
    +0.14
    0.07
    270
    +0.12
    0.07
    Negative Logits
     „,
    -1.25
     glan
    -1.23
     Teks
    -1.23
     Departement
    -1.20
     Nö
    -1.16
     kac
    -1.16
     kug
    -1.16
     inder
    -1.15
     Veter
    -1.14
     Lombar
    -1.14
    POSITIVE LOGITS
     limestones
    0.65
     tæt
    0.64
     biotite
    0.63
     hornblende
    0.60
     sandstones
    0.60
     sindaco
    0.58
     længere
    0.58
     msglen
    0.58
     ország
    0.58
    lccccc
    0.56
    Activations Density 0.581%

    No Known Activations