Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1107
    Prev
    Next
    INDEX
    Explanations

    phrases related to skepticism or disbelief

    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
    604
    +0.22
    0.6%
    225
    +0.08
    0.2%
    100
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    972
    +0.22
    0.05
    225
    +0.08
    0.05
    468
    +0.08
    0.05
    Negative Logits
    <bos>
    -1.72
    RTEX
    -0.81
     tanong
    -0.68
     bandung
    -0.67
     uhr
    -0.65
     confuso
    -0.64
     keramik
    -0.63
     rodriguez
    -0.63
     Kategor
    -0.62
     maske
    -0.62
    POSITIVE LOGITS
     adulti
    0.60
     sabato
    0.55
     onore
    0.53
    tamount
    0.52
     paradiso
    0.51
     injustice
    0.50
     violation
    0.49
     professionali
    0.48
     unacceptable
    0.48
     uffic
    0.47
    Activations Density 0.566%

    No Known Activations